diff options
Diffstat (limited to 'doc/design-paper')
| -rw-r--r-- | doc/design-paper/Makefile.am | 26 | ||||
| -rw-r--r-- | doc/design-paper/Makefile.in | 206 | ||||
| -rw-r--r-- | doc/design-paper/cell-struct.eps | 189 | ||||
| -rw-r--r-- | doc/design-paper/cell-struct.fig | 49 | ||||
| -rw-r--r-- | doc/design-paper/cell-struct.pdf | bin | 0 -> 6175 bytes | |||
| -rw-r--r-- | doc/design-paper/cell-struct.png | bin | 0 -> 6090 bytes | |||
| -rw-r--r-- | doc/design-paper/interaction.eps | 463 | ||||
| -rw-r--r-- | doc/design-paper/interaction.fig | 122 | ||||
| -rw-r--r-- | doc/design-paper/interaction.pdf | bin | 0 -> 35540 bytes | |||
| -rw-r--r-- | doc/design-paper/interaction.png | bin | 0 -> 29362 bytes | |||
| -rw-r--r-- | doc/design-paper/latex8.bst | 1124 | ||||
| -rw-r--r-- | doc/design-paper/tor-design.bib | 1093 | ||||
| -rw-r--r-- | doc/design-paper/tor-design.html | 2486 | ||||
| -rw-r--r-- | doc/design-paper/tor-design.pdf | bin | 0 -> 175246 bytes | |||
| -rw-r--r-- | doc/design-paper/tor-design.tex | 1988 | ||||
| -rw-r--r-- | doc/design-paper/usenix.sty | 98 |
16 files changed, 7844 insertions, 0 deletions
diff --git a/doc/design-paper/Makefile.am b/doc/design-paper/Makefile.am new file mode 100644 index 0000000000..0fb3d9dd27 --- /dev/null +++ b/doc/design-paper/Makefile.am @@ -0,0 +1,26 @@ + +cell-struct.eps: cell-struct.fig + fig2dev -L eps $< $@ +interaction.eps: interaction.fig + fig2dev -L eps $< $@ +cell-struct.pdf: cell-struct.fig + fig2dev -L pdf $< $@ +interaction.pdf: interaction.fig + fig2dev -L pdf $< $@ + +tor-design.ps: cell-struct.eps interaction.eps tor-design.bib tor-design.tex usenix.sty latex8.bst + latex tor-design.tex + bibtex tor-design + latex tor-design.tex + latex tor-design.tex + dvips -o $@ tor-design.dvi + +tor-design.pdf: cell-struct.pdf interaction.pdf tor-design.bib tor-design.tex usenix.sty latex8.bst + pdflatex tor-design.tex + bibtex tor-design + pdflatex tor-design.tex + pdflatex tor-design.tex + +EXTRA_DIST = cell-struct.fig interaction.fig tor-design.bib usenix.sty latex8.bst tor-design.tex + +DISTCLEANFILES = cell-struct.eps interaction.eps cell-struct.pdf interaction.pdf tor-design.aux tor-design.bbl tor-design.blg tor-design.log tor-design.dvi tor-design.ps diff --git a/doc/design-paper/Makefile.in b/doc/design-paper/Makefile.in new file mode 100644 index 0000000000..748af2ddb3 --- /dev/null +++ b/doc/design-paper/Makefile.in @@ -0,0 +1,206 @@ +# Makefile.in generated automatically by automake 1.4-p6 from Makefile.am + +# Copyright (C) 1994, 1995-8, 1999, 2001 Free Software Foundation, Inc. +# This Makefile.in is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + + +SHELL = @SHELL@ + +srcdir = @srcdir@ +top_srcdir = @top_srcdir@ +VPATH = @srcdir@ +prefix = @prefix@ +exec_prefix = @exec_prefix@ + +bindir = @bindir@ +sbindir = @sbindir@ +libexecdir = @libexecdir@ +datadir = @datadir@ +sysconfdir = @sysconfdir@ +sharedstatedir = @sharedstatedir@ +localstatedir = @localstatedir@ +libdir = @libdir@ +infodir = @infodir@ +mandir = @mandir@ +includedir = @includedir@ +oldincludedir = /usr/include + +DESTDIR = + +pkgdatadir = $(datadir)/@PACKAGE@ +pkglibdir = $(libdir)/@PACKAGE@ +pkgincludedir = $(includedir)/@PACKAGE@ + +top_builddir = ../.. + +ACLOCAL = @ACLOCAL@ +AUTOCONF = @AUTOCONF@ +AUTOMAKE = @AUTOMAKE@ +AUTOHEADER = @AUTOHEADER@ + +INSTALL = @INSTALL@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ $(AM_INSTALL_PROGRAM_FLAGS) +INSTALL_DATA = @INSTALL_DATA@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +transform = @program_transform_name@ + +NORMAL_INSTALL = : +PRE_INSTALL = : +POST_INSTALL = : +NORMAL_UNINSTALL = : +PRE_UNINSTALL = : +POST_UNINSTALL = : +host_alias = @host_alias@ +host_triplet = @host@ +BINDIR = @BINDIR@ +CC = @CC@ +CONFDIR = @CONFDIR@ +HAVE_LIB = @HAVE_LIB@ +LIB = @LIB@ +LOCALSTATEDIR = @LOCALSTATEDIR@ +LTLIB = @LTLIB@ +MAKEINFO = @MAKEINFO@ +PACKAGE = @PACKAGE@ +RANLIB = @RANLIB@ +VERSION = @VERSION@ + +EXTRA_DIST = cell-struct.fig interaction.fig tor-design.bib usenix.sty latex8.bst tor-design.tex + +DISTCLEANFILES = cell-struct.eps interaction.eps cell-struct.pdf interaction.pdf tor-design.aux tor-design.bbl tor-design.blg tor-design.log tor-design.dvi tor-design.ps +mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs +CONFIG_HEADER = ../../orconfig.h +CONFIG_CLEAN_FILES = +DIST_COMMON = Makefile.am Makefile.in + + +DISTFILES = $(DIST_COMMON) $(SOURCES) $(HEADERS) $(TEXINFOS) $(EXTRA_DIST) + +TAR = tar +GZIP_ENV = --best +all: all-redirect +.SUFFIXES: +$(srcdir)/Makefile.in: Makefile.am $(top_srcdir)/configure.in $(ACLOCAL_M4) + cd $(top_srcdir) && $(AUTOMAKE) --gnu doc/design-paper/Makefile + +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status $(BUILT_SOURCES) + cd $(top_builddir) \ + && CONFIG_FILES=$(subdir)/$@ CONFIG_HEADERS= $(SHELL) ./config.status + +tags: TAGS +TAGS: + + +distdir = $(top_builddir)/$(PACKAGE)-$(VERSION)/$(subdir) + +subdir = doc/design-paper + +distdir: $(DISTFILES) + here=`cd $(top_builddir) && pwd`; \ + top_distdir=`cd $(top_distdir) && pwd`; \ + distdir=`cd $(distdir) && pwd`; \ + cd $(top_srcdir) \ + && $(AUTOMAKE) --include-deps --build-dir=$$here --srcdir-name=$(top_srcdir) --output-dir=$$top_distdir --gnu doc/design-paper/Makefile + @for file in $(DISTFILES); do \ + d=$(srcdir); \ + if test -d $$d/$$file; then \ + cp -pr $$d/$$file $(distdir)/$$file; \ + else \ + test -f $(distdir)/$$file \ + || ln $$d/$$file $(distdir)/$$file 2> /dev/null \ + || cp -p $$d/$$file $(distdir)/$$file || :; \ + fi; \ + done +info-am: +info: info-am +dvi-am: +dvi: dvi-am +check-am: all-am +check: check-am +installcheck-am: +installcheck: installcheck-am +install-exec-am: +install-exec: install-exec-am + +install-data-am: +install-data: install-data-am + +install-am: all-am + @$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am +install: install-am +uninstall-am: +uninstall: uninstall-am +all-am: Makefile +all-redirect: all-am +install-strip: + $(MAKE) $(AM_MAKEFLAGS) AM_INSTALL_PROGRAM_FLAGS=-s install +installdirs: + + +mostlyclean-generic: + +clean-generic: + +distclean-generic: + -rm -f Makefile $(CONFIG_CLEAN_FILES) + -rm -f config.cache config.log stamp-h stamp-h[0-9]* + -test -z "$(DISTCLEANFILES)" || rm -f $(DISTCLEANFILES) + +maintainer-clean-generic: +mostlyclean-am: mostlyclean-generic + +mostlyclean: mostlyclean-am + +clean-am: clean-generic mostlyclean-am + +clean: clean-am + +distclean-am: distclean-generic clean-am + +distclean: distclean-am + +maintainer-clean-am: maintainer-clean-generic distclean-am + @echo "This command is intended for maintainers to use;" + @echo "it deletes files that may require special tools to rebuild." + +maintainer-clean: maintainer-clean-am + +.PHONY: tags distdir info-am info dvi-am dvi check check-am \ +installcheck-am installcheck install-exec-am install-exec \ +install-data-am install-data install-am install uninstall-am uninstall \ +all-redirect all-am all installdirs mostlyclean-generic \ +distclean-generic clean-generic maintainer-clean-generic clean \ +mostlyclean distclean maintainer-clean + + +cell-struct.eps: cell-struct.fig + fig2dev -L eps $< $@ +interaction.eps: interaction.fig + fig2dev -L eps $< $@ +cell-struct.pdf: cell-struct.fig + fig2dev -L pdf $< $@ +interaction.pdf: interaction.fig + fig2dev -L pdf $< $@ + +tor-design.ps: cell-struct.eps interaction.eps tor-design.bib tor-design.tex usenix.sty latex8.bst + latex tor-design.tex + bibtex tor-design + latex tor-design.tex + latex tor-design.tex + dvips -o $@ tor-design.dvi + +tor-design.pdf: cell-struct.pdf interaction.pdf tor-design.bib tor-design.tex usenix.sty latex8.bst + pdflatex tor-design.tex + bibtex tor-design + pdflatex tor-design.tex + pdflatex tor-design.tex + +# Tell versions [3.59,3.63) of GNU make to not export all variables. +# Otherwise a system limit (for SysV at least) may be exceeded. +.NOEXPORT: diff --git a/doc/design-paper/cell-struct.eps b/doc/design-paper/cell-struct.eps new file mode 100644 index 0000000000..eb9fcb8643 --- /dev/null +++ b/doc/design-paper/cell-struct.eps @@ -0,0 +1,189 @@ +%!PS-Adobe-2.0 EPSF-2.0 +%%Title: cell-struct.fig +%%Creator: fig2dev Version 3.2 Patchlevel 4 +%%CreationDate: Mon May 17 00:04:58 2004 +%%For: root@localhost.localdomain (root) +%%BoundingBox: 0 0 254 73 +%%Magnification: 1.0000 +%%EndComments +/$F2psDict 200 dict def +$F2psDict begin +$F2psDict /mtrx matrix put +/col-1 {0 setgray} bind def +/col0 {0.000 0.000 0.000 srgb} bind def +/col1 {0.000 0.000 1.000 srgb} bind def +/col2 {0.000 1.000 0.000 srgb} bind def +/col3 {0.000 1.000 1.000 srgb} bind def +/col4 {1.000 0.000 0.000 srgb} bind def +/col5 {1.000 0.000 1.000 srgb} bind def +/col6 {1.000 1.000 0.000 srgb} bind def +/col7 {1.000 1.000 1.000 srgb} bind def +/col8 {0.000 0.000 0.560 srgb} bind def +/col9 {0.000 0.000 0.690 srgb} bind def +/col10 {0.000 0.000 0.820 srgb} bind def +/col11 {0.530 0.810 1.000 srgb} bind def +/col12 {0.000 0.560 0.000 srgb} bind def +/col13 {0.000 0.690 0.000 srgb} bind def +/col14 {0.000 0.820 0.000 srgb} bind def +/col15 {0.000 0.560 0.560 srgb} bind def +/col16 {0.000 0.690 0.690 srgb} bind def +/col17 {0.000 0.820 0.820 srgb} bind def +/col18 {0.560 0.000 0.000 srgb} bind def +/col19 {0.690 0.000 0.000 srgb} bind def +/col20 {0.820 0.000 0.000 srgb} bind def +/col21 {0.560 0.000 0.560 srgb} bind def +/col22 {0.690 0.000 0.690 srgb} bind def +/col23 {0.820 0.000 0.820 srgb} bind def +/col24 {0.500 0.190 0.000 srgb} bind def +/col25 {0.630 0.250 0.000 srgb} bind def +/col26 {0.750 0.380 0.000 srgb} bind def +/col27 {1.000 0.500 0.500 srgb} bind def +/col28 {1.000 0.630 0.630 srgb} bind def +/col29 {1.000 0.750 0.750 srgb} bind def +/col30 {1.000 0.880 0.880 srgb} bind def +/col31 {1.000 0.840 0.000 srgb} bind def + +end +save +newpath 0 73 moveto 0 0 lineto 254 0 lineto 254 73 lineto closepath clip newpath +-35.3 77.2 translate +1 -1 scale + +/cp {closepath} bind def +/ef {eofill} bind def +/gr {grestore} bind def +/gs {gsave} bind def +/sa {save} bind def +/rs {restore} bind def +/l {lineto} bind def +/m {moveto} bind def +/rm {rmoveto} bind def +/n {newpath} bind def +/s {stroke} bind def +/sh {show} bind def +/slc {setlinecap} bind def +/slj {setlinejoin} bind def +/slw {setlinewidth} bind def +/srgb {setrgbcolor} bind def +/rot {rotate} bind def +/sc {scale} bind def +/sd {setdash} bind def +/ff {findfont} bind def +/sf {setfont} bind def +/scf {scalefont} bind def +/sw {stringwidth} bind def +/tr {translate} bind def +/tnt {dup dup currentrgbcolor + 4 -2 roll dup 1 exch sub 3 -1 roll mul add + 4 -2 roll dup 1 exch sub 3 -1 roll mul add + 4 -2 roll dup 1 exch sub 3 -1 roll mul add srgb} + bind def +/shd {dup dup currentrgbcolor 4 -2 roll mul 4 -2 roll mul + 4 -2 roll mul srgb} bind def +/$F2psBegin {$F2psDict begin /$F2psEnteredState save def} def +/$F2psEnd {$F2psEnteredState restore end} def + +$F2psBegin +10 setmiterlimit +0 slj 0 slc + 0.06000 0.06000 sc +% +% Fig objects follow +% +% +% here starts figure with depth 50 +% Polyline +7.500 slw +n 1200 975 m + 1200 1275 l gs col0 s gr +% Polyline +n 1725 975 m + 1725 1275 l gs col0 s gr +% Polyline +n 600 975 m 4800 975 l 4800 1275 l 600 1275 l + cp gs col0 s gr +% Polyline +n 1200 300 m + 1200 600 l gs col0 s gr +% Polyline +n 1725 300 m + 1725 600 l gs col0 s gr +% Polyline +n 600 300 m 4800 300 l 4800 600 l 600 600 l + cp gs col0 s gr +% Polyline +n 2550 975 m + 2550 1275 l gs col0 s gr +% Polyline +n 3150 975 m + 3150 1275 l gs col0 s gr +% Polyline +n 3450 975 m + 3450 1275 l gs col0 s gr +% Polyline +n 3900 975 m + 3900 1275 l gs col0 s gr +/Times-Roman ff 180.00 scf sf +675 1200 m +gs 1 -1 sc (CircID) col0 sh gr +/Times-Roman ff 180.00 scf sf +900 900 m +gs 1 -1 sc (2) col0 sh gr +/Times-Roman ff 180.00 scf sf +1275 1200 m +gs 1 -1 sc (Relay) col0 sh gr +/Times-Roman ff 180.00 scf sf +1800 1200 m +gs 1 -1 sc (StreamID) col0 sh gr +/Times-Roman ff 180.00 scf sf +2625 1200 m +gs 1 -1 sc (Digest) col0 sh gr +/Times-Roman ff 180.00 scf sf +3150 1200 m +gs 1 -1 sc (Len) col0 sh gr +/Times-Roman ff 180.00 scf sf +4200 1200 m +gs 1 -1 sc (DATA) col0 sh gr +/Times-Roman ff 180.00 scf sf +675 525 m +gs 1 -1 sc (CircID) col0 sh gr +/Times-Roman ff 180.00 scf sf +1275 525 m +gs 1 -1 sc (CMD) col0 sh gr +/Times-Roman ff 180.00 scf sf +900 225 m +gs 1 -1 sc (2) col0 sh gr +/Times-Roman ff 180.00 scf sf +1425 225 m +gs 1 -1 sc (1) col0 sh gr +/Times-Roman ff 180.00 scf sf +3225 525 m +gs 1 -1 sc (DATA) col0 sh gr +/Times-Roman ff 180.00 scf sf +3225 900 m +gs 1 -1 sc (2) col0 sh gr +/Times-Roman ff 180.00 scf sf +3450 1200 m +gs 1 -1 sc (CMD) col0 sh gr +/Times-Roman ff 180.00 scf sf +3600 900 m +gs 1 -1 sc (1) col0 sh gr +/Times-Roman ff 180.00 scf sf +3300 225 m +gs 1 -1 sc (509 bytes) col0 sh gr +/Times-Roman ff 180.00 scf sf +1425 900 m +gs 1 -1 sc (1) col0 sh gr +/Times-Roman ff 180.00 scf sf +2100 900 m +gs 1 -1 sc (2) col0 sh gr +/Times-Roman ff 180.00 scf sf +2850 900 m +gs 1 -1 sc (6) col0 sh gr +/Times-Roman ff 180.00 scf sf +4350 900 m +gs 1 -1 sc (498) col0 sh gr +% here ends figure; +$F2psEnd +rs +showpage diff --git a/doc/design-paper/cell-struct.fig b/doc/design-paper/cell-struct.fig new file mode 100644 index 0000000000..3490673ca6 --- /dev/null +++ b/doc/design-paper/cell-struct.fig @@ -0,0 +1,49 @@ +#FIG 3.2 +Landscape +Center +Inches +Letter +100.00 +Single +-2 +1200 2 +2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2 + 1200 975 1200 1275 +2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2 + 1725 975 1725 1275 +2 2 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 5 + 600 975 4800 975 4800 1275 600 1275 600 975 +2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2 + 1200 300 1200 600 +2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2 + 1725 300 1725 600 +2 2 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 5 + 600 300 4800 300 4800 600 600 600 600 300 +2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2 + 2550 975 2550 1275 +2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2 + 3150 975 3150 1275 +2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2 + 3450 975 3450 1275 +2 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2 + 3900 975 3900 1275 +4 0 0 50 -1 0 12 0.0000 4 135 510 675 1200 CircID\001 +4 0 0 50 -1 0 12 0.0000 4 135 90 900 900 2\001 +4 0 0 50 -1 0 12 0.0000 4 180 435 1275 1200 Relay\001 +4 0 0 50 -1 0 12 0.0000 4 135 735 1800 1200 StreamID\001 +4 0 0 50 -1 0 12 0.0000 4 180 510 2625 1200 Digest\001 +4 0 0 50 -1 0 12 0.0000 4 135 285 3150 1200 Len\001 +4 0 0 50 -1 0 12 0.0000 4 135 510 4200 1200 DATA\001 +4 0 0 50 -1 0 12 0.0000 4 135 510 675 525 CircID\001 +4 0 0 50 -1 0 12 0.0000 4 135 420 1275 525 CMD\001 +4 0 0 50 -1 0 12 0.0000 4 135 90 900 225 2\001 +4 0 0 50 -1 0 12 0.0000 4 135 90 1425 225 1\001 +4 0 0 50 -1 0 12 0.0000 4 135 510 3225 525 DATA\001 +4 0 0 50 -1 0 12 0.0000 4 135 90 3225 900 2\001 +4 0 0 50 -1 0 12 0.0000 4 135 420 3450 1200 CMD\001 +4 0 0 50 -1 0 12 0.0000 4 135 90 3600 900 1\001 +4 0 0 50 -1 0 12 0.0000 4 180 735 3300 225 509 bytes\001 +4 0 0 50 -1 0 12 0.0000 4 135 90 1425 900 1\001 +4 0 0 50 -1 0 12 0.0000 4 135 90 2100 900 2\001 +4 0 0 50 -1 0 12 0.0000 4 135 90 2850 900 6\001 +4 0 0 50 -1 0 12 0.0000 4 135 270 4350 900 498\001 diff --git a/doc/design-paper/cell-struct.pdf b/doc/design-paper/cell-struct.pdf Binary files differnew file mode 100644 index 0000000000..8ca52deeb9 --- /dev/null +++ b/doc/design-paper/cell-struct.pdf diff --git a/doc/design-paper/cell-struct.png b/doc/design-paper/cell-struct.png Binary files differnew file mode 100644 index 0000000000..799bcc8c18 --- /dev/null +++ b/doc/design-paper/cell-struct.png diff --git a/doc/design-paper/interaction.eps b/doc/design-paper/interaction.eps new file mode 100644 index 0000000000..9b4e3db619 --- /dev/null +++ b/doc/design-paper/interaction.eps @@ -0,0 +1,463 @@ +%!PS-Adobe-2.0 EPSF-2.0 +%%Title: interaction.fig +%%Creator: fig2dev Version 3.2 Patchlevel 3d +%%CreationDate: Sat Jan 31 05:25:23 2004 +%%For: nickm@totoro.wangafu.net () +%%BoundingBox: 0 0 449 235 +%%Magnification: 1.0000 +%%EndComments +/$F2psDict 200 dict def +$F2psDict begin +$F2psDict /mtrx matrix put +/col-1 {0 setgray} bind def +/col0 {0.000 0.000 0.000 srgb} bind def +/col1 {0.000 0.000 1.000 srgb} bind def +/col2 {0.000 1.000 0.000 srgb} bind def +/col3 {0.000 1.000 1.000 srgb} bind def +/col4 {1.000 0.000 0.000 srgb} bind def +/col5 {1.000 0.000 1.000 srgb} bind def +/col6 {1.000 1.000 0.000 srgb} bind def +/col7 {1.000 1.000 1.000 srgb} bind def +/col8 {0.000 0.000 0.560 srgb} bind def +/col9 {0.000 0.000 0.690 srgb} bind def +/col10 {0.000 0.000 0.820 srgb} bind def +/col11 {0.530 0.810 1.000 srgb} bind def +/col12 {0.000 0.560 0.000 srgb} bind def +/col13 {0.000 0.690 0.000 srgb} bind def +/col14 {0.000 0.820 0.000 srgb} bind def +/col15 {0.000 0.560 0.560 srgb} bind def +/col16 {0.000 0.690 0.690 srgb} bind def +/col17 {0.000 0.820 0.820 srgb} bind def +/col18 {0.560 0.000 0.000 srgb} bind def +/col19 {0.690 0.000 0.000 srgb} bind def +/col20 {0.820 0.000 0.000 srgb} bind def +/col21 {0.560 0.000 0.560 srgb} bind def +/col22 {0.690 0.000 0.690 srgb} bind def +/col23 {0.820 0.000 0.820 srgb} bind def +/col24 {0.500 0.190 0.000 srgb} bind def +/col25 {0.630 0.250 0.000 srgb} bind def +/col26 {0.750 0.380 0.000 srgb} bind def +/col27 {1.000 0.500 0.500 srgb} bind def +/col28 {1.000 0.630 0.630 srgb} bind def +/col29 {1.000 0.750 0.750 srgb} bind def +/col30 {1.000 0.880 0.880 srgb} bind def +/col31 {1.000 0.840 0.000 srgb} bind def + +end +save +newpath 0 235 moveto 0 0 lineto 449 0 lineto 449 235 lineto closepath clip newpath +-62.3 239.8 translate +1 -1 scale + +/cp {closepath} bind def +/ef {eofill} bind def +/gr {grestore} bind def +/gs {gsave} bind def +/sa {save} bind def +/rs {restore} bind def +/l {lineto} bind def +/m {moveto} bind def +/rm {rmoveto} bind def +/n {newpath} bind def +/s {stroke} bind def +/sh {show} bind def +/slc {setlinecap} bind def +/slj {setlinejoin} bind def +/slw {setlinewidth} bind def +/srgb {setrgbcolor} bind def +/rot {rotate} bind def +/sc {scale} bind def +/sd {setdash} bind def +/ff {findfont} bind def +/sf {setfont} bind def +/scf {scalefont} bind def +/sw {stringwidth} bind def +/tr {translate} bind def +/tnt {dup dup currentrgbcolor + 4 -2 roll dup 1 exch sub 3 -1 roll mul add + 4 -2 roll dup 1 exch sub 3 -1 roll mul add + 4 -2 roll dup 1 exch sub 3 -1 roll mul add srgb} + bind def +/shd {dup dup currentrgbcolor 4 -2 roll mul 4 -2 roll mul + 4 -2 roll mul srgb} bind def +/reencdict 12 dict def /ReEncode { reencdict begin +/newcodesandnames exch def /newfontname exch def /basefontname exch def +/basefontdict basefontname findfont def /newfont basefontdict maxlength dict def +basefontdict { exch dup /FID ne { dup /Encoding eq +{ exch dup length array copy newfont 3 1 roll put } +{ exch newfont 3 1 roll put } ifelse } { pop pop } ifelse } forall +newfont /FontName newfontname put newcodesandnames aload pop +128 1 255 { newfont /Encoding get exch /.notdef put } for +newcodesandnames length 2 idiv { newfont /Encoding get 3 1 roll put } repeat +newfontname newfont definefont pop end } def +/isovec [ +8#055 /minus 8#200 /grave 8#201 /acute 8#202 /circumflex 8#203 /tilde +8#204 /macron 8#205 /breve 8#206 /dotaccent 8#207 /dieresis +8#210 /ring 8#211 /cedilla 8#212 /hungarumlaut 8#213 /ogonek 8#214 /caron +8#220 /dotlessi 8#230 /oe 8#231 /OE +8#240 /space 8#241 /exclamdown 8#242 /cent 8#243 /sterling +8#244 /currency 8#245 /yen 8#246 /brokenbar 8#247 /section 8#250 /dieresis +8#251 /copyright 8#252 /ordfeminine 8#253 /guillemotleft 8#254 /logicalnot +8#255 /hyphen 8#256 /registered 8#257 /macron 8#260 /degree 8#261 /plusminus +8#262 /twosuperior 8#263 /threesuperior 8#264 /acute 8#265 /mu 8#266 /paragraph +8#267 /periodcentered 8#270 /cedilla 8#271 /onesuperior 8#272 /ordmasculine +8#273 /guillemotright 8#274 /onequarter 8#275 /onehalf +8#276 /threequarters 8#277 /questiondown 8#300 /Agrave 8#301 /Aacute +8#302 /Acircumflex 8#303 /Atilde 8#304 /Adieresis 8#305 /Aring +8#306 /AE 8#307 /Ccedilla 8#310 /Egrave 8#311 /Eacute +8#312 /Ecircumflex 8#313 /Edieresis 8#314 /Igrave 8#315 /Iacute +8#316 /Icircumflex 8#317 /Idieresis 8#320 /Eth 8#321 /Ntilde 8#322 /Ograve +8#323 /Oacute 8#324 /Ocircumflex 8#325 /Otilde 8#326 /Odieresis 8#327 /multiply +8#330 /Oslash 8#331 /Ugrave 8#332 /Uacute 8#333 /Ucircumflex +8#334 /Udieresis 8#335 /Yacute 8#336 /Thorn 8#337 /germandbls 8#340 /agrave +8#341 /aacute 8#342 /acircumflex 8#343 /atilde 8#344 /adieresis 8#345 /aring +8#346 /ae 8#347 /ccedilla 8#350 /egrave 8#351 /eacute +8#352 /ecircumflex 8#353 /edieresis 8#354 /igrave 8#355 /iacute +8#356 /icircumflex 8#357 /idieresis 8#360 /eth 8#361 /ntilde 8#362 /ograve +8#363 /oacute 8#364 /ocircumflex 8#365 /otilde 8#366 /odieresis 8#367 /divide +8#370 /oslash 8#371 /ugrave 8#372 /uacute 8#373 /ucircumflex +8#374 /udieresis 8#375 /yacute 8#376 /thorn 8#377 /ydieresis] def +/Times-Bold /Times-Bold-iso isovec ReEncode +/Times-Roman /Times-Roman-iso isovec ReEncode +/$F2psBegin {$F2psDict begin /$F2psEnteredState save def} def +/$F2psEnd {$F2psEnteredState restore end} def + +$F2psBegin +10 setmiterlimit + 0.06000 0.06000 sc +% +% Fig objects follow +% +% Polyline +15.000 slw +n 6000 300 m + 6000 3975 l gs col0 s gr +% Polyline +7.500 slw +gs clippath +3615 555 m 3615 495 l 3464 495 l 3584 525 l 3464 555 l cp +eoclip +n 1200 525 m + 3600 525 l gs col0 s gr gr + +% arrowhead +n 3464 555 m 3584 525 l 3464 495 l 3464 555 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +1185 795 m 1185 855 l 1336 855 l 1216 825 l 1336 795 l cp +eoclip +n 3600 825 m + 1200 825 l gs col0 s gr gr + +% arrowhead +n 1336 795 m 1216 825 l 1336 855 l 1336 795 l cp gs 0.00 setgray ef gr col0 s +% Polyline +15.000 slw +n 1200 300 m + 1200 3975 l gs col0 s gr +% Polyline +7.500 slw +gs clippath +3615 1155 m 3615 1095 l 3464 1095 l 3584 1125 l 3464 1155 l cp +eoclip +n 1200 1125 m + 3600 1125 l gs col0 s gr gr + +% arrowhead +n 3464 1155 m 3584 1125 l 3464 1095 l 3464 1155 l cp gs 0.00 setgray ef gr col0 s +% Polyline +15.000 slw +n 3600 300 m + 3600 3975 l gs col0 s gr +% Polyline +7.500 slw +gs clippath +6015 1230 m 6015 1170 l 5864 1170 l 5984 1200 l 5864 1230 l cp +eoclip +n 3600 1200 m + 6000 1200 l gs col0 s gr gr + +% arrowhead +n 5864 1230 m 5984 1200 l 5864 1170 l 5864 1230 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +3585 1470 m 3585 1530 l 3736 1530 l 3616 1500 l 3736 1470 l cp +eoclip +n 6000 1500 m + 3600 1500 l gs col0 s gr gr + +% arrowhead +n 3736 1470 m 3616 1500 l 3736 1530 l 3736 1470 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +1185 1545 m 1185 1605 l 1336 1605 l 1216 1575 l 1336 1545 l cp +eoclip +n 3600 1575 m + 1200 1575 l gs col0 s gr gr + +% arrowhead +n 1336 1545 m 1216 1575 l 1336 1605 l 1336 1545 l cp gs 0.00 setgray ef gr col0 s +% Polyline + [15 45] 45 sd +n 1050 1800 m + 8325 1800 l gs col0 s gr [] 0 sd +% Polyline +gs clippath +3615 2130 m 3615 2070 l 3464 2070 l 3584 2100 l 3464 2130 l cp +eoclip +n 1200 2100 m + 3600 2100 l gs col0 s gr gr + +% arrowhead +n 3464 2130 m 3584 2100 l 3464 2070 l 3464 2130 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +6015 2205 m 6015 2145 l 5864 2145 l 5984 2175 l 5864 2205 l cp +eoclip +n 3600 2175 m + 6000 2175 l gs col0 s gr gr + +% arrowhead +n 5864 2205 m 5984 2175 l 5864 2145 l 5864 2205 l cp gs 0.00 setgray ef gr col0 s +% Polyline + [60] 0 sd +gs clippath +8190 2430 m 8190 2370 l 8039 2370 l 8159 2400 l 8039 2430 l cp +5985 2370 m 5985 2430 l 6136 2430 l 6016 2400 l 6136 2370 l cp +eoclip +n 6000 2400 m + 8175 2400 l gs col0 s gr gr + [] 0 sd +% arrowhead +n 6136 2370 m 6016 2400 l 6136 2430 l 6136 2370 l cp gs 0.00 setgray ef gr col0 s +% arrowhead +n 8039 2430 m 8159 2400 l 8039 2370 l 8039 2430 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +3585 2520 m 3585 2580 l 3736 2580 l 3616 2550 l 3736 2520 l cp +eoclip +n 6000 2550 m + 3600 2550 l gs col0 s gr gr + +% arrowhead +n 3736 2520 m 3616 2550 l 3736 2580 l 3736 2520 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +1185 2595 m 1185 2655 l 1336 2655 l 1216 2625 l 1336 2595 l cp +eoclip +n 3600 2625 m + 1200 2625 l gs col0 s gr gr + +% arrowhead +n 1336 2595 m 1216 2625 l 1336 2655 l 1336 2595 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +3615 3030 m 3615 2970 l 3464 2970 l 3584 3000 l 3464 3030 l cp +eoclip +n 1200 3000 m + 3600 3000 l gs col0 s gr gr + +% arrowhead +n 3464 3030 m 3584 3000 l 3464 2970 l 3464 3030 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +6015 3105 m 6015 3045 l 5864 3045 l 5984 3075 l 5864 3105 l cp +eoclip +n 3600 3075 m + 6000 3075 l gs col0 s gr gr + +% arrowhead +n 5864 3105 m 5984 3075 l 5864 3045 l 5864 3105 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +8190 3180 m 8190 3120 l 8039 3120 l 8159 3150 l 8039 3180 l cp +eoclip +n 6000 3150 m + 8175 3150 l gs col0 s gr gr + +% arrowhead +n 8039 3180 m 8159 3150 l 8039 3120 l 8039 3180 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +5985 3420 m 5985 3480 l 6136 3480 l 6016 3450 l 6136 3420 l cp +eoclip +n 8175 3450 m + 6000 3450 l gs col0 s gr gr + +% arrowhead +n 6136 3420 m 6016 3450 l 6136 3480 l 6136 3420 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +5985 3495 m 5985 3555 l 6136 3555 l 6016 3525 l 6136 3495 l cp +eoclip +n 8175 3525 m + 6000 3525 l gs col0 s gr gr + +% arrowhead +n 6136 3495 m 6016 3525 l 6136 3555 l 6136 3495 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +5985 3570 m 5985 3630 l 6136 3630 l 6016 3600 l 6136 3570 l cp +eoclip +n 8175 3600 m + 6000 3600 l gs col0 s gr gr + +% arrowhead +n 6136 3570 m 6016 3600 l 6136 3630 l 6136 3570 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +3585 3495 m 3585 3555 l 3736 3555 l 3616 3525 l 3736 3495 l cp +eoclip +n 6000 3525 m + 3600 3525 l gs col0 s gr gr + +% arrowhead +n 3736 3495 m 3616 3525 l 3736 3555 l 3736 3495 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +3585 3645 m 3585 3705 l 3736 3705 l 3616 3675 l 3736 3645 l cp +eoclip +n 6000 3675 m + 3600 3675 l gs col0 s gr gr + +% arrowhead +n 3736 3645 m 3616 3675 l 3736 3705 l 3736 3645 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +3585 3570 m 3585 3630 l 3736 3630 l 3616 3600 l 3736 3570 l cp +eoclip +n 6000 3600 m + 3600 3600 l gs col0 s gr gr + +% arrowhead +n 3736 3570 m 3616 3600 l 3736 3630 l 3736 3570 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +1185 3645 m 1185 3705 l 1336 3705 l 1216 3675 l 1336 3645 l cp +eoclip +n 3600 3675 m + 1200 3675 l gs col0 s gr gr + +% arrowhead +n 1336 3645 m 1216 3675 l 1336 3705 l 1336 3645 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +1185 3720 m 1185 3780 l 1336 3780 l 1216 3750 l 1336 3720 l cp +eoclip +n 3600 3750 m + 1200 3750 l gs col0 s gr gr + +% arrowhead +n 1336 3720 m 1216 3750 l 1336 3780 l 1336 3720 l cp gs 0.00 setgray ef gr col0 s +% Polyline +gs clippath +1185 3795 m 1185 3855 l 1336 3855 l 1216 3825 l 1336 3795 l cp +eoclip +n 3600 3825 m + 1200 3825 l gs col0 s gr gr + +% arrowhead +n 1336 3795 m 1216 3825 l 1336 3855 l 1336 3795 l cp gs 0.00 setgray ef gr col0 s +% Polyline +15.000 slw +n 8175 300 m + 8175 3975 l gs col0 s gr +% Polyline +7.500 slw +n 6300 825 m 7950 825 l 7950 1725 l 6300 1725 l + cp gs col7 1.00 shd ef gr gs col0 s gr +/Times-Bold-iso ff 180.00 scf sf +3375 225 m +gs 1 -1 sc (OR 1) col0 sh gr +/Times-Bold-iso ff 180.00 scf sf +1050 225 m +gs 1 -1 sc (Alice) col0 sh gr +/Times-Bold-iso ff 180.00 scf sf +5775 225 m +gs 1 -1 sc (OR 2) col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +6075 3075 m +gs 1 -1 sc ("HTTP GET...") col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +4800 3975 m +gs 1 -1 sc (. . .) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +7125 3975 m +gs 1 -1 sc (. . .) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +2400 3975 m +gs 1 -1 sc (. . .) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +7125 2325 m +gs 1 -1 sc (\(TCP handshake\)) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Bold-iso ff 180.00 scf sf +7875 225 m +gs 1 -1 sc (website) col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +7125 1425 m +gs 1 -1 sc ({X}--AES encryption) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +7125 1200 m +gs 1 -1 sc (E\(x\)--RSA encryption) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +7125 975 m +gs 1 -1 sc (Legend:) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +2400 225 m +gs 1 -1 sc (\(link is TLS-encrypted\)) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +1275 1050 m +gs 1 -1 sc (Relay c1{Extend, OR2, E\(g^x2\)}) col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +1275 2025 m +gs 1 -1 sc (Relay c1{{Begin <website>:80}}) col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +3525 1500 m +gs 1 -1 sc (Relay c1{Extended, g^y2, H\(K2\)}) dup sw pop neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +3675 2100 m +gs 1 -1 sc (Relay c2{Begin <website>:80}) col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +3525 2550 m +gs 1 -1 sc (Relay c1{{Connected}}) dup sw pop neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +5925 2475 m +gs 1 -1 sc (Relay c2{Connected}) dup sw pop neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +1275 2925 m +gs 1 -1 sc (Relay c1{{Data, "HTTP GET..."}}) col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +3675 3000 m +gs 1 -1 sc (Relay c2{Data, "HTTP GET..."}) col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +4800 225 m +gs 1 -1 sc (\(link is TLS-encryped\)) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +7050 225 m +gs 1 -1 sc (\(unencrypted\)) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +7125 1650 m +gs 1 -1 sc (cN--a circID) dup sw pop 2 div neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +3525 3600 m +gs 1 -1 sc (Relay c1{{Data, \(response\)}}) dup sw pop neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +8100 3375 m +gs 1 -1 sc (\(response\)) dup sw pop neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +5925 3450 m +gs 1 -1 sc (Relay c2{Data, \(response\)}) dup sw pop neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +5925 1425 m +gs 1 -1 sc (Created c2, g^y2, H\(K2\)) dup sw pop neg 0 rm col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +3675 1125 m +gs 1 -1 sc (Create c2, E\(g^x2\)) col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +1275 450 m +gs 1 -1 sc (Create c1, E\(g^x1\)) col0 sh gr +/Times-Roman-iso ff 150.00 scf sf +3525 750 m +gs 1 -1 sc (Created c1, g^y1, H\(K1\)) dup sw pop neg 0 rm col0 sh gr +$F2psEnd +rs diff --git a/doc/design-paper/interaction.fig b/doc/design-paper/interaction.fig new file mode 100644 index 0000000000..a7b49e0a52 --- /dev/null +++ b/doc/design-paper/interaction.fig @@ -0,0 +1,122 @@ +#FIG 3.2 +Landscape +Center +Inches +Letter +100.00 +Single +-2 +1200 2 +2 1 0 2 0 7 50 0 -1 0.000 0 0 -1 0 0 2 + 6000 300 6000 3975 +2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 1200 525 3600 525 +2 1 0 1 0 7 50 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3600 825 1200 825 +2 1 0 2 0 7 50 0 -1 0.000 0 0 -1 0 0 2 + 1200 300 1200 3975 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 1200 1125 3600 1125 +2 1 0 2 0 7 50 0 -1 0.000 0 0 -1 0 0 2 + 3600 300 3600 3975 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3600 1200 6000 1200 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 6000 1500 3600 1500 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3600 1575 1200 1575 +2 1 2 1 0 7 50 0 -1 3.000 0 0 -1 0 0 2 + 1050 1800 8325 1800 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 1200 2100 3600 2100 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3600 2175 6000 2175 +2 1 1 1 0 7 50 0 -1 4.000 0 0 -1 1 1 2 + 1 1 1.00 60.00 120.00 + 1 1 1.00 60.00 120.00 + 6000 2400 8175 2400 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 6000 2550 3600 2550 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3600 2625 1200 2625 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 1200 3000 3600 3000 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3600 3075 6000 3075 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 6000 3150 8175 3150 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 8175 3450 6000 3450 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 8175 3525 6000 3525 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 8175 3600 6000 3600 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 6000 3525 3600 3525 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 6000 3675 3600 3675 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 6000 3600 3600 3600 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3600 3675 1200 3675 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3600 3750 1200 3750 +2 1 0 1 0 7 50 0 -1 3.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3600 3825 1200 3825 +2 1 0 2 0 7 50 0 -1 0.000 0 0 -1 0 0 2 + 8175 300 8175 3975 +2 2 0 1 0 7 50 0 20 3.000 0 0 -1 0 0 5 + 6300 825 7950 825 7950 1725 6300 1725 6300 825 +4 0 0 50 0 2 12 0.0000 4 135 450 3375 225 OR 1\001 +4 0 0 50 0 2 12 0.0000 4 135 420 1050 225 Alice\001 +4 0 0 50 0 2 12 0.0000 4 135 450 5775 225 OR 2\001 +4 0 0 50 0 0 10 0.0000 4 105 960 6075 3075 "HTTP GET..."\001 +4 1 0 50 0 0 10 0.0000 4 15 135 4800 3975 . . .\001 +4 1 0 50 0 0 10 0.0000 4 15 135 7125 3975 . . .\001 +4 1 0 50 0 0 10 0.0000 4 15 135 2400 3975 . . .\001 +4 1 0 50 0 0 10 0.0000 4 135 1050 7125 2325 (TCP handshake)\001 +4 0 0 50 0 2 12 0.0000 4 135 630 7875 225 website\001 +4 1 0 50 0 0 10 0.0000 4 135 1335 7125 1425 {X}--AES encryption\001 +4 1 0 50 0 0 10 0.0000 4 135 1410 7125 1200 E(x)--RSA encryption\001 +4 1 0 50 0 0 10 0.0000 4 135 480 7125 975 Legend:\001 +4 1 0 50 0 0 10 0.0000 4 135 1455 2400 225 (link is TLS-encrypted)\001 +4 0 0 50 0 0 10 0.0000 4 135 2085 1275 1050 Relay c1{Extend, OR2, E(g^x2)}\001 +4 0 0 50 0 0 10 0.0000 4 135 1965 1275 2025 Relay c1{{Begin <website>:80}}\001 +4 2 0 50 0 0 10 0.0000 4 135 2190 3525 1500 Relay c1{Extended, g^y2, H(K2)}\001 +4 0 0 50 0 0 10 0.0000 4 135 1845 3675 2100 Relay c2{Begin <website>:80}\001 +4 2 0 50 0 0 10 0.0000 4 135 1410 3525 2550 Relay c1{{Connected}}\001 +4 2 0 50 0 0 10 0.0000 4 135 1290 5925 2475 Relay c2{Connected}\001 +4 0 0 50 0 0 10 0.0000 4 135 2085 1275 2925 Relay c1{{Data, "HTTP GET..."}}\001 +4 0 0 50 0 0 10 0.0000 4 135 1965 3675 3000 Relay c2{Data, "HTTP GET..."}\001 +4 1 0 50 0 0 10 0.0000 4 135 1365 4800 225 (link is TLS-encryped)\001 +4 1 0 50 0 0 10 0.0000 4 135 870 7050 225 (unencrypted)\001 +4 1 0 50 0 0 10 0.0000 4 105 780 7125 1650 cN--a circID\001 +4 2 0 50 0 0 10 0.0000 4 135 1860 3525 3600 Relay c1{{Data, (response)}}\001 +4 2 0 50 0 0 10 0.0000 4 135 645 8100 3375 (response)\001 +4 2 0 50 0 0 10 0.0000 4 135 1650 5925 3450 Relay c2{Data, (response)}\001 +4 2 0 50 0 0 10 0.0000 4 135 1545 5925 1425 Created c2, g^y2, H(K2)\001 +4 0 0 50 0 0 10 0.0000 4 135 1170 3675 1125 Create c2, E(g^x2)\001 +4 0 0 50 0 0 10 0.0000 4 135 1170 1275 450 Create c1, E(g^x1)\001 +4 2 0 50 0 0 10 0.0000 4 135 1545 3525 750 Created c1, g^y1, H(K1)\001 diff --git a/doc/design-paper/interaction.pdf b/doc/design-paper/interaction.pdf Binary files differnew file mode 100644 index 0000000000..8def0add59 --- /dev/null +++ b/doc/design-paper/interaction.pdf diff --git a/doc/design-paper/interaction.png b/doc/design-paper/interaction.png Binary files differnew file mode 100644 index 0000000000..2bb904fcd9 --- /dev/null +++ b/doc/design-paper/interaction.png diff --git a/doc/design-paper/latex8.bst b/doc/design-paper/latex8.bst new file mode 100644 index 0000000000..2dd3249633 --- /dev/null +++ b/doc/design-paper/latex8.bst @@ -0,0 +1,1124 @@ + +% --------------------------------------------------------------- +% +% $Id$ +% +% by Paolo.Ienne@di.epfl.ch +% + +% --------------------------------------------------------------- +% +% no guarantee is given that the format corresponds perfectly to +% IEEE 8.5" x 11" Proceedings, but most features should be ok. +% +% --------------------------------------------------------------- +% +% `latex8' from BibTeX standard bibliography style `abbrv' +% version 0.99a for BibTeX versions 0.99a or later, LaTeX version 2.09. +% Copyright (C) 1985, all rights reserved. +% Copying of this file is authorized only if either +% (1) you make absolutely no changes to your copy, including name, or +% (2) if you do make changes, you name it something other than +% btxbst.doc, plain.bst, unsrt.bst, alpha.bst, and abbrv.bst. +% This restriction helps ensure that all standard styles are identical. +% The file btxbst.doc has the documentation for this style. + +ENTRY + { address + author + booktitle + chapter + edition + editor + howpublished + institution + journal + key + month + note + number + organization + pages + publisher + school + series + title + type + volume + year + } + {} + { label } + +INTEGERS { output.state before.all mid.sentence after.sentence after.block } + +FUNCTION {init.state.consts} +{ #0 'before.all := + #1 'mid.sentence := + #2 'after.sentence := + #3 'after.block := +} + +STRINGS { s t } + +FUNCTION {output.nonnull} +{ 's := + output.state mid.sentence = + { ", " * write$ } + { output.state after.block = + { add.period$ write$ + newline$ + "\newblock " write$ + } + { output.state before.all = + 'write$ + { add.period$ " " * write$ } + if$ + } + if$ + mid.sentence 'output.state := + } + if$ + s +} + +FUNCTION {output} +{ duplicate$ empty$ + 'pop$ + 'output.nonnull + if$ +} + +FUNCTION {output.check} +{ 't := + duplicate$ empty$ + { pop$ "empty " t * " in " * cite$ * warning$ } + 'output.nonnull + if$ +} + +FUNCTION {output.bibitem} +{ newline$ + "\bibitem{" write$ + cite$ write$ + "}" write$ + newline$ + "" + before.all 'output.state := +} + +FUNCTION {fin.entry} +{ add.period$ + write$ + newline$ +} + +FUNCTION {new.block} +{ output.state before.all = + 'skip$ + { after.block 'output.state := } + if$ +} + +FUNCTION {new.sentence} +{ output.state after.block = + 'skip$ + { output.state before.all = + 'skip$ + { after.sentence 'output.state := } + if$ + } + if$ +} + +FUNCTION {not} +{ { #0 } + { #1 } + if$ +} + +FUNCTION {and} +{ 'skip$ + { pop$ #0 } + if$ +} + +FUNCTION {or} +{ { pop$ #1 } + 'skip$ + if$ +} + +FUNCTION {new.block.checka} +{ empty$ + 'skip$ + 'new.block + if$ +} + +FUNCTION {new.block.checkb} +{ empty$ + swap$ empty$ + and + 'skip$ + 'new.block + if$ +} + +FUNCTION {new.sentence.checka} +{ empty$ + 'skip$ + 'new.sentence + if$ +} + +FUNCTION {new.sentence.checkb} +{ empty$ + swap$ empty$ + and + 'skip$ + 'new.sentence + if$ +} + +FUNCTION {field.or.null} +{ duplicate$ empty$ + { pop$ "" } + 'skip$ + if$ +} + +FUNCTION {emphasize} +{ duplicate$ empty$ + { pop$ "" } + { "{\em " swap$ * "}" * } + if$ +} + +INTEGERS { nameptr namesleft numnames } + +FUNCTION {format.names} +{ 's := + #1 'nameptr := + s num.names$ 'numnames := + numnames 'namesleft := + { namesleft #0 > } + { s nameptr "{f.~}{vv~}{ll}{, jj}" format.name$ 't := + nameptr #1 > + { namesleft #1 > + { ", " * t * } + { numnames #2 > + { "," * } + 'skip$ + if$ + t "others" = + { " et~al." * } + { " and " * t * } + if$ + } + if$ + } + 't + if$ + nameptr #1 + 'nameptr := + + namesleft #1 - 'namesleft := + } + while$ +} + +FUNCTION {format.authors} +{ author empty$ + { "" } + { author format.names } + if$ +} + +FUNCTION {format.editors} +{ editor empty$ + { "" } + { editor format.names + editor num.names$ #1 > + { ", editors" * } + { ", editor" * } + if$ + } + if$ +} + +FUNCTION {format.title} +{ title empty$ + { "" } + { title "t" change.case$ } + if$ +} + +FUNCTION {n.dashify} +{ 't := + "" + { t empty$ not } + { t #1 #1 substring$ "-" = + { t #1 #2 substring$ "--" = not + { "--" * + t #2 global.max$ substring$ 't := + } + { { t #1 #1 substring$ "-" = } + { "-" * + t #2 global.max$ substring$ 't := + } + while$ + } + if$ + } + { t #1 #1 substring$ * + t #2 global.max$ substring$ 't := + } + if$ + } + while$ +} + +FUNCTION {format.date} +{ year empty$ + { month empty$ + { "" } + { "there's a month but no year in " cite$ * warning$ + month + } + if$ + } + { month empty$ + 'year + { month " " * year * } + if$ + } + if$ +} + +FUNCTION {format.btitle} +{ title emphasize +} + +FUNCTION {tie.or.space.connect} +{ duplicate$ text.length$ #3 < + { "~" } + { " " } + if$ + swap$ * * +} + +FUNCTION {either.or.check} +{ empty$ + 'pop$ + { "can't use both " swap$ * " fields in " * cite$ * warning$ } + if$ +} + +FUNCTION {format.bvolume} +{ volume empty$ + { "" } + { "volume" volume tie.or.space.connect + series empty$ + 'skip$ + { " of " * series emphasize * } + if$ + "volume and number" number either.or.check + } + if$ +} + +FUNCTION {format.number.series} +{ volume empty$ + { number empty$ + { series field.or.null } + { output.state mid.sentence = + { "number" } + { "Number" } + if$ + number tie.or.space.connect + series empty$ + { "there's a number but no series in " cite$ * warning$ } + { " in " * series * } + if$ + } + if$ + } + { "" } + if$ +} + +FUNCTION {format.edition} +{ edition empty$ + { "" } + { output.state mid.sentence = + { edition "l" change.case$ " edition" * } + { edition "t" change.case$ " edition" * } + if$ + } + if$ +} + +INTEGERS { multiresult } + +FUNCTION {multi.page.check} +{ 't := + #0 'multiresult := + { multiresult not + t empty$ not + and + } + { t #1 #1 substring$ + duplicate$ "-" = + swap$ duplicate$ "," = + swap$ "+" = + or or + { #1 'multiresult := } + { t #2 global.max$ substring$ 't := } + if$ + } + while$ + multiresult +} + +FUNCTION {format.pages} +{ pages empty$ + { "" } + { pages multi.page.check + { "pages" pages n.dashify tie.or.space.connect } + { "page" pages tie.or.space.connect } + if$ + } + if$ +} + +FUNCTION {format.vol.num.pages} +{ volume field.or.null + number empty$ + 'skip$ + { "(" number * ")" * * + volume empty$ + { "there's a number but no volume in " cite$ * warning$ } + 'skip$ + if$ + } + if$ + pages empty$ + 'skip$ + { duplicate$ empty$ + { pop$ format.pages } + { ":" * pages n.dashify * } + if$ + } + if$ +} + +FUNCTION {format.chapter.pages} +{ chapter empty$ + 'format.pages + { type empty$ + { "chapter" } + { type "l" change.case$ } + if$ + chapter tie.or.space.connect + pages empty$ + 'skip$ + { ", " * format.pages * } + if$ + } + if$ +} + +FUNCTION {format.in.ed.booktitle} +{ booktitle empty$ + { "" } + { editor empty$ + { "In " booktitle emphasize * } + { "In " format.editors * ", " * booktitle emphasize * } + if$ + } + if$ +} + +FUNCTION {empty.misc.check} + +{ author empty$ title empty$ howpublished empty$ + month empty$ year empty$ note empty$ + and and and and and + key empty$ not and + { "all relevant fields are empty in " cite$ * warning$ } + 'skip$ + if$ +} + +FUNCTION {format.thesis.type} +{ type empty$ + 'skip$ + { pop$ + type "t" change.case$ + } + if$ +} + +FUNCTION {format.tr.number} +{ type empty$ + { "Technical Report" } + 'type + if$ + number empty$ + { "t" change.case$ } + { number tie.or.space.connect } + if$ +} + +FUNCTION {format.article.crossref} +{ key empty$ + { journal empty$ + { "need key or journal for " cite$ * " to crossref " * crossref * + warning$ + "" + } + { "In {\em " journal * "\/}" * } + if$ + } + { "In " key * } + if$ + " \cite{" * crossref * "}" * +} + +FUNCTION {format.crossref.editor} +{ editor #1 "{vv~}{ll}" format.name$ + editor num.names$ duplicate$ + #2 > + { pop$ " et~al." * } + { #2 < + 'skip$ + { editor #2 "{ff }{vv }{ll}{ jj}" format.name$ "others" = + { " et~al." * } + { " and " * editor #2 "{vv~}{ll}" format.name$ * } + if$ + } + if$ + } + if$ +} + +FUNCTION {format.book.crossref} +{ volume empty$ + { "empty volume in " cite$ * "'s crossref of " * crossref * warning$ + "In " + } + { "Volume" volume tie.or.space.connect + " of " * + } + if$ + editor empty$ + editor field.or.null author field.or.null = + or + { key empty$ + { series empty$ + { "need editor, key, or series for " cite$ * " to crossref " * + crossref * warning$ + "" * + } + { "{\em " * series * "\/}" * } + if$ + } + { key * } + if$ + } + { format.crossref.editor * } + if$ + " \cite{" * crossref * "}" * +} + +FUNCTION {format.incoll.inproc.crossref} +{ editor empty$ + editor field.or.null author field.or.null = + or + { key empty$ + { booktitle empty$ + { "need editor, key, or booktitle for " cite$ * " to crossref " * + crossref * warning$ + "" + } + { "In {\em " booktitle * "\/}" * } + if$ + } + { "In " key * } + if$ + } + { "In " format.crossref.editor * } + if$ + " \cite{" * crossref * "}" * +} + +FUNCTION {article} +{ output.bibitem + format.authors "author" output.check + new.block + format.title "title" output.check + new.block + crossref missing$ + { journal emphasize "journal" output.check + format.vol.num.pages output + format.date "year" output.check + } + { format.article.crossref output.nonnull + format.pages output + } + if$ + new.block + note output + fin.entry +} + +FUNCTION {book} +{ output.bibitem + author empty$ + { format.editors "author and editor" output.check } + { format.authors output.nonnull + crossref missing$ + { "author and editor" editor either.or.check } + 'skip$ + if$ + } + if$ + new.block + format.btitle "title" output.check + crossref missing$ + { format.bvolume output + new.block + format.number.series output + new.sentence + publisher "publisher" output.check + address output + } + { new.block + format.book.crossref output.nonnull + } + if$ + format.edition output + format.date "year" output.check + new.block + note output + fin.entry +} + +FUNCTION {booklet} +{ output.bibitem + format.authors output + new.block + format.title "title" output.check + howpublished address new.block.checkb + howpublished output + address output + format.date output + new.block + note output + fin.entry +} + +FUNCTION {inbook} +{ output.bibitem + author empty$ + { format.editors "author and editor" output.check } + { format.authors output.nonnull + + crossref missing$ + { "author and editor" editor either.or.check } + 'skip$ + if$ + } + if$ + new.block + format.btitle "title" output.check + crossref missing$ + { format.bvolume output + format.chapter.pages "chapter and pages" output.check + new.block + format.number.series output + new.sentence + publisher "publisher" output.check + address output + } + { format.chapter.pages "chapter and pages" output.check + new.block + format.book.crossref output.nonnull + } + if$ + format.edition output + format.date "year" output.check + new.block + note output + fin.entry +} + +FUNCTION {incollection} +{ output.bibitem + format.authors "author" output.check + new.block + format.title "title" output.check + new.block + crossref missing$ + { format.in.ed.booktitle "booktitle" output.check + format.bvolume output + format.number.series output + format.chapter.pages output + new.sentence + publisher "publisher" output.check + address output + format.edition output + format.date "year" output.check + } + { format.incoll.inproc.crossref output.nonnull + format.chapter.pages output + } + if$ + new.block + note output + fin.entry +} + +FUNCTION {inproceedings} +{ output.bibitem + format.authors "author" output.check + new.block + format.title "title" output.check + new.block + crossref missing$ + { format.in.ed.booktitle "booktitle" output.check + format.bvolume output + format.number.series output + format.pages output + address empty$ + { organization publisher new.sentence.checkb + organization output + publisher output + format.date "year" output.check + } + { address output.nonnull + format.date "year" output.check + new.sentence + organization output + publisher output + } + if$ + } + { format.incoll.inproc.crossref output.nonnull + format.pages output + } + if$ + new.block + note output + fin.entry +} + +FUNCTION {conference} { inproceedings } + +FUNCTION {manual} +{ output.bibitem + author empty$ + { organization empty$ + 'skip$ + { organization output.nonnull + address output + } + if$ + } + { format.authors output.nonnull } + if$ + new.block + format.btitle "title" output.check + author empty$ + { organization empty$ + { address new.block.checka + address output + } + 'skip$ + if$ + } + { organization address new.block.checkb + organization output + address output + } + if$ + format.edition output + format.date output + new.block + note output + fin.entry +} + +FUNCTION {mastersthesis} +{ output.bibitem + format.authors "author" output.check + new.block + format.title "title" output.check + new.block + "Master's thesis" format.thesis.type output.nonnull + school "school" output.check + address output + format.date "year" output.check + new.block + note output + fin.entry +} + +FUNCTION {misc} +{ output.bibitem + format.authors output + title howpublished new.block.checkb + format.title output + howpublished new.block.checka + howpublished output + format.date output + new.block + note output + fin.entry + empty.misc.check +} + +FUNCTION {phdthesis} +{ output.bibitem + format.authors "author" output.check + new.block + format.btitle "title" output.check + new.block + "PhD thesis" format.thesis.type output.nonnull + school "school" output.check + address output + format.date "year" output.check + new.block + note output + fin.entry +} + +FUNCTION {proceedings} +{ output.bibitem + editor empty$ + { organization output } + { format.editors output.nonnull } + + if$ + new.block + format.btitle "title" output.check + format.bvolume output + format.number.series output + address empty$ + { editor empty$ + { publisher new.sentence.checka } + { organization publisher new.sentence.checkb + organization output + } + if$ + publisher output + format.date "year" output.check + } + { address output.nonnull + format.date "year" output.check + new.sentence + editor empty$ + 'skip$ + { organization output } + if$ + publisher output + } + if$ + new.block + note output + fin.entry +} + +FUNCTION {techreport} +{ output.bibitem + format.authors "author" output.check + new.block + format.title "title" output.check + new.block + format.tr.number output.nonnull + institution "institution" output.check + address output + format.date "year" output.check + new.block + note output + fin.entry +} + +FUNCTION {unpublished} +{ output.bibitem + format.authors "author" output.check + new.block + format.title "title" output.check + new.block + note "note" output.check + format.date output + fin.entry +} + +FUNCTION {default.type} { misc } + +MACRO {jan} {"Jan."} + +MACRO {feb} {"Feb."} + +MACRO {mar} {"Mar."} + +MACRO {apr} {"Apr."} + +MACRO {may} {"May"} + +MACRO {jun} {"June"} + +MACRO {jul} {"July"} + +MACRO {aug} {"Aug."} + +MACRO {sep} {"Sept."} + +MACRO {oct} {"Oct."} + +MACRO {nov} {"Nov."} + +MACRO {dec} {"Dec."} + +MACRO {acmcs} {"ACM Comput. Surv."} + +MACRO {acta} {"Acta Inf."} + +MACRO {cacm} {"Commun. ACM"} + +MACRO {ibmjrd} {"IBM J. Res. Dev."} + +MACRO {ibmsj} {"IBM Syst.~J."} + +MACRO {ieeese} {"IEEE Trans. Softw. Eng."} + +MACRO {ieeetc} {"IEEE Trans. Comput."} + +MACRO {ieeetcad} + {"IEEE Trans. Comput.-Aided Design Integrated Circuits"} + +MACRO {ipl} {"Inf. Process. Lett."} + +MACRO {jacm} {"J.~ACM"} + +MACRO {jcss} {"J.~Comput. Syst. Sci."} + +MACRO {scp} {"Sci. Comput. Programming"} + +MACRO {sicomp} {"SIAM J. Comput."} + +MACRO {tocs} {"ACM Trans. Comput. Syst."} + +MACRO {tods} {"ACM Trans. Database Syst."} + +MACRO {tog} {"ACM Trans. Gr."} + +MACRO {toms} {"ACM Trans. Math. Softw."} + +MACRO {toois} {"ACM Trans. Office Inf. Syst."} + +MACRO {toplas} {"ACM Trans. Prog. Lang. Syst."} + +MACRO {tcs} {"Theoretical Comput. Sci."} + +READ + +FUNCTION {sortify} +{ purify$ + "l" change.case$ +} + +INTEGERS { len } + +FUNCTION {chop.word} +{ 's := + 'len := + s #1 len substring$ = + { s len #1 + global.max$ substring$ } + 's + if$ +} + +FUNCTION {sort.format.names} +{ 's := + #1 'nameptr := + "" + s num.names$ 'numnames := + numnames 'namesleft := + { namesleft #0 > } + { nameptr #1 > + { " " * } + 'skip$ + if$ + s nameptr "{vv{ } }{ll{ }}{ f{ }}{ jj{ }}" format.name$ 't := + nameptr numnames = t "others" = and + { "et al" * } + { t sortify * } + if$ + nameptr #1 + 'nameptr := + namesleft #1 - 'namesleft := + } + while$ +} + +FUNCTION {sort.format.title} +{ 't := + "A " #2 + "An " #3 + "The " #4 t chop.word + chop.word + chop.word + sortify + #1 global.max$ substring$ +} + +FUNCTION {author.sort} +{ author empty$ + { key empty$ + { "to sort, need author or key in " cite$ * warning$ + "" + } + { key sortify } + if$ + } + { author sort.format.names } + if$ +} + +FUNCTION {author.editor.sort} +{ author empty$ + { editor empty$ + { key empty$ + { "to sort, need author, editor, or key in " cite$ * warning$ + "" + } + { key sortify } + if$ + } + { editor sort.format.names } + if$ + } + { author sort.format.names } + if$ +} + +FUNCTION {author.organization.sort} +{ author empty$ + + { organization empty$ + { key empty$ + { "to sort, need author, organization, or key in " cite$ * warning$ + "" + } + { key sortify } + if$ + } + { "The " #4 organization chop.word sortify } + if$ + } + { author sort.format.names } + if$ +} + +FUNCTION {editor.organization.sort} +{ editor empty$ + { organization empty$ + { key empty$ + { "to sort, need editor, organization, or key in " cite$ * warning$ + "" + } + { key sortify } + if$ + } + { "The " #4 organization chop.word sortify } + if$ + } + { editor sort.format.names } + if$ +} + +FUNCTION {presort} +{ type$ "book" = + type$ "inbook" = + or + 'author.editor.sort + { type$ "proceedings" = + 'editor.organization.sort + { type$ "manual" = + 'author.organization.sort + 'author.sort + if$ + } + if$ + } + if$ + " " + * + year field.or.null sortify + * + " " + * + title field.or.null + sort.format.title + * + #1 entry.max$ substring$ + 'sort.key$ := +} + +ITERATE {presort} + +SORT + +STRINGS { longest.label } + +INTEGERS { number.label longest.label.width } + +FUNCTION {initialize.longest.label} +{ "" 'longest.label := + #1 'number.label := + #0 'longest.label.width := +} + +FUNCTION {longest.label.pass} +{ number.label int.to.str$ 'label := + number.label #1 + 'number.label := + label width$ longest.label.width > + { label 'longest.label := + label width$ 'longest.label.width := + } + 'skip$ + if$ +} + +EXECUTE {initialize.longest.label} + +ITERATE {longest.label.pass} + +FUNCTION {begin.bib} +{ preamble$ empty$ + 'skip$ + { preamble$ write$ newline$ } + if$ + "\begin{thebibliography}{" longest.label * + "}\setlength{\itemsep}{-1ex}\small" * write$ newline$ +} + +EXECUTE {begin.bib} + +EXECUTE {init.state.consts} + +ITERATE {call.type$} + +FUNCTION {end.bib} +{ newline$ + "\end{thebibliography}" write$ newline$ +} + +EXECUTE {end.bib} + +% end of file latex8.bst +% --------------------------------------------------------------- + + + diff --git a/doc/design-paper/tor-design.bib b/doc/design-paper/tor-design.bib new file mode 100644 index 0000000000..cf60f2cd22 --- /dev/null +++ b/doc/design-paper/tor-design.bib @@ -0,0 +1,1093 @@ + +% fix me +@misc{tannenbaum96, + author = "Andrew Tannenbaum", + title = "Computer Networks", + year = "1996", + publisher = "Prentice Hall, 3rd edition", +} + +@article{ meadows96, + author = "Catherine Meadows", + title = "The {NRL} Protocol Analyzer: An Overview", + journal = "Journal of Logic Programming", + volume = "26", + number = "2", + pages = "113--131", + year = "1996", +} +@inproceedings{kesdogan:pet2002, + title = {Unobservable Surfing on the World Wide Web: Is Private Information Retrieval an + alternative to the MIX based Approach?}, + author = {Dogan Kesdogan and Mark Borning and Michael Schmeink}, + booktitle = {Privacy Enhancing Technologies (PET 2002)}, + year = {2002}, + month = {April}, + editor = {Roger Dingledine and Paul Syverson}, + publisher = {Springer-Verlag, LNCS 2482}, +} + +@inproceedings{statistical-disclosure, + title = {Statistical Disclosure Attacks}, + author = {George Danezis}, + booktitle = {Security and Privacy in the Age of Uncertainty ({SEC2003})}, + organization = {{IFIP TC11}}, + year = {2003}, + month = {May}, + address = {Athens}, + pages = {421--426}, + publisher = {Kluwer}, +} + +@inproceedings{limits-open, + title = {Limits of Anonymity in Open Environments}, + author = {Dogan Kesdogan and Dakshi Agrawal and Stefan Penz}, + booktitle = {Information Hiding Workshop (IH 2002)}, + year = {2002}, + month = {October}, + editor = {Fabien Petitcolas}, + publisher = {Springer-Verlag, LNCS 2578}, +} + +@inproceedings{isdn-mixes, + title = {{ISDN-mixes: Untraceable communication with very small bandwidth overhead}}, + author = {Andreas Pfitzmann and Birgit Pfitzmann and Michael Waidner}, + booktitle = {GI/ITG Conference on Communication in Distributed Systems}, + year = {1991}, + month = {February}, + pages = {451-463}, +} + + +@Article{jerichow-jsac98, + author = {Anja Jerichow and Jan M\"{u}ller and Andreas + Pfitzmann and Birgit Pfitzmann and Michael Waidner}, + title = {Real-Time Mixes: A Bandwidth-Efficient Anonymity Protocol}, + journal = {IEEE Journal on Selected Areas in Communications}, + year = 1998, + volume = 16, + number = 4, + pages = {495--509}, + month = {May} +} + +@inproceedings{tarzan:ccs02, + title = {Tarzan: A Peer-to-Peer Anonymizing Network Layer}, + author = {Michael J. Freedman and Robert Morris}, + booktitle = {9th {ACM} {C}onference on {C}omputer and {C}ommunications + {S}ecurity ({CCS 2002})}, + year = {2002}, + month = {November}, + address = {Washington, DC}, +} + +@inproceedings{cebolla, + title = {{Cebolla: Pragmatic IP Anonymity}}, + author = {Zach Brown}, + booktitle = {Ottawa Linux Symposium}, + year = {2002}, + month = {June}, +} + +@inproceedings{eax, + author = "M. Bellare and P. Rogaway and D. Wagner", + title = {The {EAX} Mode of Operation: A Two-Pass Authenticated-Encryption Scheme Optimized for Simplicity and Efficiency}, + booktitle = {Fast Software Encryption 2004}, + month = {February}, + year = {2004}, +} + +@misc{darkside, + title = {{The Dark Side of the Web: An Open Proxy's View}}, + author = {Vivek S. Pai and Limin Wang and KyoungSoo Park and Ruoming Pang and Larry Peterson}, + note = {\newline \url{http://codeen.cs.princeton.edu/}}, +} +% note = {Submitted to HotNets-II. \url{http://codeen.cs.princeton.edu/}}, + +@Misc{anonymizer, + key = {anonymizer}, + title = {The {Anonymizer}}, + note = {\url{http://anonymizer.com/}} +} + +@Misc{privoxy, + key = {privoxy}, + title = {{Privoxy}}, + note = {\url{http://www.privoxy.org/}} +} + +@inproceedings{anonnet, + title = {{Analysis of an Anonymity Network for Web Browsing}}, + author = {Marc Rennhard and Sandro Rafaeli and Laurent Mathy and Bernhard Plattner and + David Hutchison}, + booktitle = {{IEEE 7th Intl. Workshop on Enterprise Security (WET ICE + 2002)}}, + year = {2002}, + month = {June}, + address = {Pittsburgh, USA}, +} +% pages = {49--54}, + +@inproceedings{econymics, + title = {On the Economics of Anonymity}, + author = {Alessandro Acquisti and Roger Dingledine and Paul Syverson}, + booktitle = {Financial Cryptography}, + year = {2003}, + editor = {Rebecca N. Wright}, + publisher = {Springer-Verlag, LNCS 2742}, +} + +@inproceedings{defensive-dropping, + title = {Timing Analysis in Low-Latency Mix-Based Systems}, + author = {Brian N. Levine and Michael K. Reiter and Chenxi Wang and Matthew Wright}, + booktitle = {Financial Cryptography}, + year = {2004}, + editor = {Ari Juels}, + publisher = {Springer-Verlag, LNCS (forthcoming)}, +} + +@inproceedings{morphmix:fc04, + title = {Practical Anonymity for the Masses with MorphMix}, + author = {Marc Rennhard and Bernhard Plattner}, + booktitle = {Financial Cryptography}, + year = {2004}, + editor = {Ari Juels}, + publisher = {Springer-Verlag, LNCS (forthcoming)}, +} + +@inproceedings{eternity, + title = {The Eternity Service}, + author = {Ross Anderson}, + booktitle = {Pragocrypt '96}, + year = {1996}, +} + %note = {\url{http://www.cl.cam.ac.uk/users/rja14/eternity/eternity.html}}, + + +@inproceedings{minion-design, + title = {Mixminion: Design of a Type {III} Anonymous Remailer Protocol}, + author = {George Danezis and Roger Dingledine and Nick Mathewson}, + booktitle = {2003 IEEE Symposium on Security and Privacy}, + year = {2003}, + month = {May}, + publisher = {IEEE CS}, + pages = {2--15}, +} + %note = {\url{http://mixminion.net/minion-design.pdf}}, + +@inproceedings{ rao-pseudonymity, + author = "Josyula R. Rao and Pankaj Rohatgi", + title = "Can Pseudonymity Really Guarantee Privacy?", + booktitle = "Proceedings of the Ninth USENIX Security Symposium", + year = {2000}, + month = Aug, + publisher = {USENIX}, + pages = "85--96", +} + %note = {\url{http://www.usenix.org/publications/library/proceedings/sec2000/ +%full_papers/rao/rao.pdf}}, + +@InProceedings{pfitzmann90how, + author = "Birgit Pfitzmann and Andreas Pfitzmann", + title = "How to Break the Direct {RSA}-Implementation of {MIXes}", + booktitle = {Eurocrypt 89}, + publisher = {Springer-Verlag, LNCS 434}, + year = {1990}, + note = {\url{http://citeseer.nj.nec.com/pfitzmann90how.html}}, +} + +@Misc{tor-spec, + author = {Roger Dingledine and Nick Mathewson}, + title = {Tor Protocol Specifications}, + note = {\url{http://freehaven.net/tor/tor-spec.txt}}, +} + +@InProceedings{BM:mixencrypt, + author = {M{\"o}ller, Bodo}, + title = {Provably Secure Public-Key Encryption for Length-Preserving Chaumian Mixes}, + booktitle = {{CT-RSA} 2003}, + publisher = {Springer-Verlag, LNCS 2612}, + year = 2003, +} + +@InProceedings{back01, + author = {Adam Back and Ulf M\"oller and Anton Stiglic}, + title = {Traffic Analysis Attacks and Trade-Offs in Anonymity Providing Systems}, + booktitle = {Information Hiding (IH 2001)}, + pages = {245--257}, + year = 2001, + editor = {Ira S. Moskowitz}, + publisher = {Springer-Verlag, LNCS 2137}, +} + %note = {\newline \url{http://www.cypherspace.org/adam/pubs/traffic.pdf}}, + +@InProceedings{rackoff93cryptographic, + author = {Charles Rackoff and Daniel R. Simon}, + title = {Cryptographic Defense Against Traffic Analysis}, + booktitle = {{ACM} Symposium on Theory of Computing}, + pages = {672--681}, + year = {1993}, +} + %note = {\url{http://research.microsoft.com/crypto/dansimon/me.htm}}, + +@InProceedings{freehaven-berk, + author = {Roger Dingledine and Michael J. Freedman and David Molnar}, + title = {The Free Haven Project: Distributed Anonymous Storage Service}, + booktitle = {Designing Privacy Enhancing Technologies: Workshop + on Design Issue in Anonymity and Unobservability}, + year = {2000}, + month = {July}, + editor = {H. Federrath}, + publisher = {Springer-Verlag, LNCS 2009}, +} + %note = {\url{http://freehaven.net/papers.html}}, + +@InProceedings{raymond00, + author = {J. F. Raymond}, + title = {{Traffic Analysis: Protocols, Attacks, Design Issues, + and Open Problems}}, + booktitle = {Designing Privacy Enhancing Technologies: Workshop + on Design Issue in Anonymity and Unobservability}, + year = 2000, + month = {July}, + pages = {10-29}, + editor = {H. Federrath}, + publisher = {Springer-Verlag, LNCS 2009}, +} + +@InProceedings{sybil, + author = "John Douceur", + title = {{The Sybil Attack}}, + booktitle = "Proceedings of the 1st International Peer To Peer Systems Workshop (IPTPS)", + month = Mar, + year = 2002, +} + +@InProceedings{trickle02, + author = {Andrei Serjantov and Roger Dingledine and Paul Syverson}, + title = {From a Trickle to a Flood: Active Attacks on Several + Mix Types}, + booktitle = {Information Hiding (IH 2002)}, + year = {2002}, + editor = {Fabien Petitcolas}, + publisher = {Springer-Verlag, LNCS 2578}, +} + +@InProceedings{langos02, + author = {Oliver Berthold and Heinrich Langos}, + title = {Dummy Traffic Against Long Term Intersection Attacks}, + booktitle = {Privacy Enhancing Technologies (PET 2002)}, + year = {2002}, + editor = {Roger Dingledine and Paul Syverson}, + publisher = {Springer-Verlag, LNCS 2482} +} + + +@InProceedings{hintz-pet02, + author = {Andrew Hintz}, + title = {Fingerprinting Websites Using Traffic Analysis}, + booktitle = {Privacy Enhancing Technologies (PET 2002)}, + pages = {171--178}, + year = 2002, + editor = {Roger Dingledine and Paul Syverson}, + publisher = {Springer-Verlag, LNCS 2482} +} + +@InProceedings{or-discex00, + author = {Paul Syverson and Michael Reed and David Goldschlag}, + title = {{O}nion {R}outing Access Configurations}, + booktitle = {DARPA Information Survivability Conference and + Exposition (DISCEX 2000)}, + year = {2000}, + publisher = {IEEE CS Press}, + pages = {34--40}, + volume = {1}, +} + %note = {\newline \url{http://www.onion-router.net/Publications.html}}, + +@Inproceedings{or-pet00, + title = {{Towards an Analysis of Onion Routing Security}}, + author = {Paul Syverson and Gene Tsudik and Michael Reed and + Carl Landwehr}, + booktitle = {Designing Privacy Enhancing Technologies: Workshop + on Design Issue in Anonymity and Unobservability}, + year = 2000, + month = {July}, + pages = {96--114}, + editor = {H. Federrath}, + publisher = {Springer-Verlag, LNCS 2009}, +} + %note = {\url{http://www.onion-router.net/Publications/WDIAU-2000.ps.gz}}, + +@Inproceedings{freenet-pets00, + title = {Freenet: A Distributed Anonymous Information Storage + and Retrieval System}, + author = {Ian Clarke and Oskar Sandberg and Brandon Wiley and + Theodore W. Hong}, + booktitle = {Designing Privacy Enhancing Technologies: Workshop + on Design Issue in Anonymity and Unobservability}, + year = 2000, + month = {July}, + pages = {46--66}, + editor = {H. Federrath}, + publisher = {Springer-Verlag, LNCS 2009}, +} + %note = {\url{http://citeseer.nj.nec.com/clarke00freenet.html}}, + +@InProceedings{or-ih96, + author = {David M. Goldschlag and Michael G. Reed and Paul + F. Syverson}, + title = {Hiding Routing Information}, + booktitle = {Information Hiding, First International Workshop}, + pages = {137--150}, + year = 1996, + editor = {R. Anderson}, + month = {May}, + publisher = {Springer-Verlag, LNCS 1174}, +} + +@InProceedings{federrath-ih96, + author = {Hannes Federrath and Anja Jerichow and Andreas Pfitzmann}, + title = {{MIXes} in Mobile Communication Systems: Location + Management with Privacy}, + booktitle = {Information Hiding, First International Workshop}, + pages = {121--135}, + year = 1996, + editor = {R. Anderson}, + month = {May}, + publisher = {Springer-Verlag, LNCS 1174}, +} + + +@InProceedings{reed-protocols97, + author = {Michael G. Reed and Paul F. Syverson and David + M. Goldschlag}, + title = {Protocols Using Anonymous Connections: Mobile Applications}, + booktitle = {Security Protocols: 5th International Workshop}, + pages = {13--23}, + year = 1997, + editor = {Bruce Christianson and Bruno Crispo and Mark Lomas + and Michael Roe}, + month = {April}, + publisher = {Springer-Verlag, LNCS 1361} +} + + + +@Article{or-jsac98, + author = {Michael G. Reed and Paul F. Syverson and David + M. Goldschlag}, + title = {Anonymous Connections and Onion Routing}, + journal = {IEEE Journal on Selected Areas in Communications}, + year = 1998, + volume = 16, + number = 4, + pages = {482--494}, + month = {May}, +} + %note = {\url{http://www.onion-router.net/Publications/JSAC-1998.ps.gz}} + +@Misc{TLS, + author = {T. Dierks and C. Allen}, + title = {The {TLS} {P}rotocol --- {V}ersion 1.0}, + howpublished = {IETF RFC 2246}, + month = {January}, + year = {1999}, +} +%note = {\url{http://www.rfc-editor.org/rfc/rfc2246.txt}}, + +@Misc{SMTP, + author = {J. Postel}, + title = {Simple {M}ail {T}ransfer {P}rotocol}, + howpublished = {IETF RFC 2821 (also STD0010)}, + month = {April}, + year = {2001}, + note = {\url{http://www.rfc-editor.org/rfc/rfc2821.txt}}, +} + +@Misc{IMAP, + author = {M. Crispin}, + title = {Internet {M}essage {A}ccess {P}rotocol --- {V}ersion 4rev1}, + howpublished = {IETF RFC 2060}, + month = {December}, + year = {1996}, + note = {\url{http://www.rfc-editor.org/rfc/rfc2060.txt}}, +} + +@misc{pipenet, + title = {PipeNet 1.1}, + author = {Wei Dai}, + year = 1996, + month = {August}, + howpublished = {Usenet post}, + note = {\url{http://www.eskimo.com/~weidai/pipenet.txt} First mentioned + in a post to the cypherpunks list, Feb.\ 1995.}, +} + + +@Misc{POP3, + author = {J. Myers and M. Rose}, + title = {Post {O}ffice {P}rotocol --- {V}ersion 3}, + howpublished = {IETF RFC 1939 (also STD0053)}, + month = {May}, + year = {1996}, + note = {\url{http://www.rfc-editor.org/rfc/rfc1939.txt}}, +} + + +@InProceedings{shuffle, + author = {C. Andrew Neff}, + title = {A Verifiable Secret Shuffle and its Application to E-Voting}, + booktitle = {8th ACM Conference on Computer and Communications + Security (CCS-8)}, + pages = {116--125}, + year = 2001, + editor = {P. Samarati}, + month = {November}, + publisher = {ACM Press}, +} + %note = {\url{http://www.votehere.net/ada_compliant/ourtechnology/ + % technicaldocs/shuffle.pdf}}, + +@InProceedings{dolev91, + author = {Danny Dolev and Cynthia Dwork and Moni Naor}, + title = {Non-Malleable Cryptography}, + booktitle = {23rd ACM Symposium on the Theory of Computing (STOC)}, + pages = {542--552}, + year = 1991, + note = {Updated version at + \url{http://citeseer.nj.nec.com/dolev00nonmalleable.html}}, +} + +@TechReport{rsw96, + author = {Ronald L. Rivest and Adi Shamir and David A. Wagner}, + title = {Time-lock puzzles and timed-release Crypto}, + year = 1996, + type = {MIT LCS technical memo}, + number = {MIT/LCS/TR-684}, + month = {February}, + note = {\newline \url{http://citeseer.nj.nec.com/rivest96timelock.html}}, +} + +@InProceedings{web-mix, + author = {Oliver Berthold and Hannes Federrath and Stefan K\"opsell}, + title = {Web {MIX}es: A system for anonymous and unobservable + {I}nternet access}, + booktitle = {Designing Privacy Enhancing Technologies: Workshop + on Design Issue in Anonymity and Unobservability}, + editor = {H. Federrath}, + publisher = {Springer-Verlag, LNCS 2009}, + year = {2000}, +} +% pages = {115--129}, + +@InProceedings{disad-free-routes, + author = {Oliver Berthold and Andreas Pfitzmann and Ronny Standtke}, + title = {The disadvantages of free {MIX} routes and how to overcome + them}, + booktitle = {Designing Privacy Enhancing Technologies: Workshop + on Design Issue in Anonymity and Unobservability}, + pages = {30--45}, + year = 2000, + editor = {H. Federrath}, + publisher = {Springer-Verlag, LNCS 2009}, +} + %note = {\url{http://www.tik.ee.ethz.ch/~weiler/lehre/netsec/Unterlagen/anon/ + % disadvantages_berthold.pdf}}, + +@InProceedings{boneh00, + author = {Dan Boneh and Moni Naor}, + title = {Timed Commitments}, + booktitle = {Advances in Cryptology -- {CRYPTO} 2000}, + pages = {236--254}, + year = 2000, + publisher = {Springer-Verlag, LNCS 1880}, + note = {\newline \url{http://crypto.stanford.edu/~dabo/abstracts/timedcommit.html}}, +} + +@InProceedings{goldschlag98, + author = {David M. Goldschlag and Stuart G. Stubblebine}, + title = {Publicly Verifiable Lotteries: Applications of + Delaying Functions}, + booktitle = {Financial Cryptography}, + pages = {214--226}, + year = 1998, + publisher = {Springer-Verlag, LNCS 1465}, + note = {\newline \url{http://citeseer.nj.nec.com/goldschlag98publicly.html}}, +} + +@InProceedings{syverson98, + author = {Paul Syverson}, + title = {Weakly Secret Bit Commitment: Applications to + Lotteries and Fair Exchange}, + booktitle = {Computer Security Foundations Workshop (CSFW11)}, + pages = {2--13}, + year = 1998, + address = {Rockport Massachusetts}, + month = {June}, + publisher = {IEEE CS Press}, + note = {\newline \url{http://chacs.nrl.navy.mil/publications/CHACS/1998/}}, +} + +@Misc{shoup-iso, + author = {Victor Shoup}, + title = {A Proposal for an {ISO} {S}tandard for Public Key Encryption (version 2.1)}, + note = {Revised December 20, 2001. \url{http://www.shoup.net/papers/}}, +} + +@Misc{shoup-oaep, + author = {Victor Shoup}, + title = {{OAEP} Reconsidered}, + howpublished = {{IACR} e-print 2000/060}, + note = {\newline \url{http://eprint.iacr.org/2000/060/}}, +} + +@Misc{oaep-still-alive, + author = {E. Fujisaki and D. Pointcheval and T. Okamoto and J. Stern}, + title = {{RSA}-{OAEP} is Still Alive!}, + howpublished = {{IACR} e-print 2000/061}, + note = {\newline \url{http://eprint.iacr.org/2000/061/}}, +} + +@misc{echolot, + author = {Peter Palfrader}, + title = {Echolot: a pinger for anonymous remailers}, + note = {\url{http://www.palfrader.org/echolot/}}, +} + +@Misc{mixmaster-attacks, + author = {Lance Cottrell}, + title = {Mixmaster and Remailer Attacks}, + note = {\url{http://www.obscura.com/~loki/remailer/remailer-essay.html}}, +} + +@Misc{mixmaster-spec, + author = {Ulf M{\"o}ller and Lance Cottrell and Peter + Palfrader and Len Sassaman}, + title = {Mixmaster {P}rotocol --- {V}ersion 2}, + year = {2003}, + month = {July}, + howpublished = {Draft}, + note = {\url{http://www.abditum.com/mixmaster-spec.txt}}, +} + +@InProceedings{puzzles-tls, + author = "Drew Dean and Adam Stubblefield", + title = {{Using Client Puzzles to Protect TLS}}, + booktitle = "Proceedings of the 10th USENIX Security Symposium", + year = {2001}, + month = Aug, + publisher = {USENIX}, +} + +@InProceedings{breadpudding, + author = {Markus Jakobsson and Ari Juels}, + title = {Proofs of Work and Bread Pudding Protocols}, + booktitle = {Proceedings of the IFIP TC6 and TC11 Joint Working + Conference on Communications and Multimedia Security + (CMS '99)}, + year = 1999, + month = {September}, + publisher = {Kluwer} +} + +@Misc{hashcash, + author = {Adam Back}, + title = {Hash cash}, + note = {\newline \url{http://www.cypherspace.org/~adam/hashcash/}}, +} + +@InProceedings{oreilly-acc, + author = {Roger Dingledine and Michael J. Freedman and David Molnar}, + title = {Accountability}, + booktitle = {Peer-to-peer: Harnessing the Benefits of a Disruptive + Technology}, + year = {2001}, + publisher = {O'Reilly and Associates}, +} + + +@InProceedings{han, + author = {Yongfei Han}, + title = {Investigation of non-repudiation protocols}, + booktitle = {ACISP '96}, + year = 1996, + publisher = {Springer-Verlag}, +} + + +@Misc{socks5, + key = {socks5}, + title = {{SOCKS} {P}rotocol {V}ersion 5}, + howpublished= {IETF RFC 1928}, + month = {March}, + year = 1996, + note = {\url{http://www.ietf.org/rfc/rfc1928.txt}} +} + +@InProceedings{abe, + author = {Masayuki Abe}, + title = {Universally Verifiable {MIX} With Verification Work Independent of + The Number of {MIX} Servers}, + booktitle = {{EUROCRYPT} 1998}, + year = {1998}, + publisher = {Springer-Verlag, LNCS 1403}, +} + +@InProceedings{desmedt, + author = {Yvo Desmedt and Kaoru Kurosawa}, + title = {How To Break a Practical {MIX} and Design a New One}, + booktitle = {{EUROCRYPT} 2000}, + year = {2000}, + publisher = {Springer-Verlag, LNCS 1803}, + note = {\url{http://citeseer.nj.nec.com/447709.html}}, +} + +@InProceedings{mitkuro, + author = {M. Mitomo and K. Kurosawa}, + title = {{Attack for Flash MIX}}, + booktitle = {{ASIACRYPT} 2000}, + year = {2000}, + publisher = {Springer-Verlag, LNCS 1976}, + note = {\newline \url{http://citeseer.nj.nec.com/450148.html}}, +} + +@InProceedings{hybrid-mix, + author = {M. Ohkubo and M. Abe}, + title = {A {L}ength-{I}nvariant {H}ybrid {MIX}}, + booktitle = {Advances in Cryptology - {ASIACRYPT} 2000}, + year = {2000}, + publisher = {Springer-Verlag, LNCS 1976}, +} + +@InProceedings{PShuffle, + author = {Jun Furukawa and Kazue Sako}, + title = {An Efficient Scheme for Proving a Shuffle}, + editor = {Joe Kilian}, + booktitle = {CRYPTO 2001}, + year = {2001}, + publisher = {Springer-Verlag, LNCS 2139}, +} + + +@InProceedings{jakobsson-optimally, + author = "Markus Jakobsson and Ari Juels", + title = "An Optimally Robust Hybrid Mix Network (Extended Abstract)", + booktitle = {Principles of Distributed Computing - {PODC} '01}, + year = "2001", + publisher = {ACM Press}, + note = {\url{http://citeseer.nj.nec.com/492015.html}}, +} + +@InProceedings{kesdogan, + author = {D. Kesdogan and M. Egner and T. B\"uschkes}, + title = {Stop-and-Go {MIX}es Providing Probabilistic Anonymity in an Open + System}, + booktitle = {Information Hiding (IH 1998)}, + year = {1998}, + publisher = {Springer-Verlag, LNCS 1525}, +} + %note = {\url{http://www.cl.cam.ac.uk/~fapp2/ihw98/ihw98-sgmix.pdf}}, + +@InProceedings{socks4, + author = {David Koblas and Michelle R. Koblas}, + title = {{SOCKS}}, + booktitle = {UNIX Security III Symposium (1992 USENIX Security + Symposium)}, + pages = {77--83}, + year = 1992, + publisher = {USENIX}, +} + +@InProceedings{flash-mix, + author = {Markus Jakobsson}, + title = {Flash {M}ixing}, + booktitle = {Principles of Distributed Computing - {PODC} '99}, + year = {1999}, + publisher = {ACM Press}, + note = {\newline \url{http://citeseer.nj.nec.com/jakobsson99flash.html}}, +} + +@InProceedings{SK, + author = {Joe Kilian and Kazue Sako}, + title = {Receipt-Free {MIX}-Type Voting Scheme - A Practical Solution to + the Implementation of a Voting Booth}, + booktitle = {EUROCRYPT '95}, + year = {1995}, + publisher = {Springer-Verlag}, +} + +@InProceedings{OAEP, + author = {M. Bellare and P. Rogaway}, + year = {1994}, + booktitle = {EUROCRYPT '94}, + title = {Optimal {A}symmetric {E}ncryption {P}adding : How To Encrypt With + {RSA}}, + publisher = {Springer-Verlag}, + note = {\newline \url{http://www-cse.ucsd.edu/users/mihir/papers/oaep.html}}, +} +@inproceedings{babel, + title = {Mixing {E}-mail With {B}abel}, + author = {Ceki G\"ulc\"u and Gene Tsudik}, + booktitle = {{Network and Distributed Security Symposium (NDSS 96)}}, + year = 1996, + month = {February}, + pages = {2--16}, + publisher = {IEEE}, +} + %note = {\url{http://citeseer.nj.nec.com/2254.html}}, + +@Misc{rprocess, + author = {RProcess}, + title = {Selective Denial of Service Attacks}, + note = {\newline \url{http://www.eff.org/pub/Privacy/Anonymity/1999\_09\_DoS\_remail\_vuln.html}}, +} + +@Article{remailer-history, + author = {Sameer Parekh}, + title = {Prospects for Remailers}, + journal = {First Monday}, + volume = {1}, + number = {2}, + month = {August}, + year = {1996}, + note = {\url{http://www.firstmonday.dk/issues/issue2/remailers/}}, +} + +@Article{chaum-mix, + author = {David Chaum}, + title = {Untraceable electronic mail, return addresses, and digital pseudo-nyms}, + journal = {Communications of the ACM}, + year = {1981}, + volume = {4}, + number = {2}, + month = {February}, +} + %note = {\url{http://www.eskimo.com/~weidai/mix-net.txt}}, + +@InProceedings{nym-alias-net, + author = {David Mazi\`{e}res and M. Frans Kaashoek}, + title = {{The Design, Implementation and Operation of an Email + Pseudonym Server}}, + booktitle = {$5^{th}$ ACM Conference on Computer and + Communications Security (CCS'98)}, + year = 1998, + publisher = {ACM Press}, +} + %note = {\newline \url{http://www.scs.cs.nyu.edu/~dm/}}, + +@InProceedings{tangler, + author = {Marc Waldman and David Mazi\`{e}res}, + title = {Tangler: A Censorship-Resistant Publishing System + Based on Document Entanglements}, + booktitle = {$8^{th}$ ACM Conference on Computer and + Communications Security (CCS-8)}, + pages = {86--135}, + year = 2001, + publisher = {ACM Press}, +} + %note = {\url{http://www.scs.cs.nyu.edu/~dm/}} + +@misc{neochaum, + author = {Tim May}, + title = {Payment mixes for anonymity}, + howpublished = {E-mail archived at + \url{http://\newline www.inet-one.com/cypherpunks/dir.2000.02.28-2000.03.05/msg00334.html}}, +} + +@misc{helsingius, + author = {J. Helsingius}, + title = {{\tt anon.penet.fi} press release}, + note = {\newline \url{http://www.penet.fi/press-english.html}}, +} + +@InProceedings{garay97secure, + author = {J. Garay and R. Gennaro and C. Jutla and T. Rabin}, + title = {Secure distributed storage and retrieval}, + booktitle = {11th International Workshop, WDAG '97}, + pages = {275--289}, + year = {1997}, + publisher = {Springer-Verlag, LNCS 1320}, + note = {\newline \url{http://citeseer.nj.nec.com/garay97secure.html}}, +} + +@InProceedings{PIK, + author = {C. Park and K. Itoh and K. Kurosawa}, + title = {Efficient anonymous channel and all/nothing election scheme}, + booktitle = {Advances in Cryptology -- {EUROCRYPT} '93}, + pages = {248--259}, + publisher = {Springer-Verlag, LNCS 765}, +} + +@Misc{pgpfaq, + key = {PGP}, + title = {{PGP} {FAQ}}, + note = {\newline \url{http://www.faqs.org/faqs/pgp-faq/}}, +} + +@Article{riordan-schneier, + author = {James Riordan and Bruce Schneier}, + title = {A Certified E-mail Protocol with No Trusted Third Party}, + journal = {13th Annual Computer Security Applications Conference}, + month = {December}, + year = {1998}, + note = {\newline \url{http://www.counterpane.com/certified-email.html}}, +} + + +@Article{crowds-tissec, + author = {Michael K. Reiter and Aviel D. Rubin}, + title = {Crowds: Anonymity for Web Transactions}, + journal = {ACM TISSEC}, + year = 1998, + volume = 1, + number = 1, + pages = {66--92}, + month = {June}, +} + %note = {\url{http://citeseer.nj.nec.com/284739.html}} + +@Article{crowds-dimacs, + author = {Michael K. Reiter and Aviel D. Rubin}, + title = {Crowds: Anonymity for Web Transactions}, + journal = {{DIMACS} Technical Report (Revised)}, + volume = {97}, + number = {15}, + month = {August}, + year = {1997}, +} + +@Misc{advogato, + author = {Raph Levien}, + title = {Advogato's Trust Metric}, + note = {\newline \url{http://www.advogato.org/trust-metric.html}}, +} + +@InProceedings{publius, + author = {Marc Waldman and Aviel Rubin and Lorrie Cranor}, + title = {Publius: {A} robust, tamper-evident, censorship-resistant and + source-anonymous web publishing system}, + booktitle = {Proc. 9th USENIX Security Symposium}, + pages = {59--72}, + year = {2000}, + month = {August}, +} + %note = {\newline \url{http://citeseer.nj.nec.com/waldman00publius.html}}, + +@Misc{freedom-nyms, + author = {Russell Samuels}, + title = {Untraceable Nym Creation on the {F}reedom {N}etwork}, + year = {1999}, + month = {November}, + day = {21}, + note = {\newline \url{http://www.freedom.net/products/whitepapers/white11.html}}, +} + +@techreport{freedom2-arch, + title = {Freedom Systems 2.0 Architecture}, + author = {Philippe Boucher and Adam Shostack and Ian Goldberg}, + institution = {Zero Knowledge Systems, {Inc.}}, + year = {2000}, + month = {December}, + type = {White Paper}, + day = {18}, +} + +@techreport{freedom21-security, + title = {Freedom Systems 2.1 Security Issues and Analysis}, + author = {Adam Back and Ian Goldberg and Adam Shostack}, + institution = {Zero Knowledge Systems, {Inc.}}, + year = {2001}, + month = {May}, + type = {White Paper}, +} + +@inproceedings{cfs:sosp01, + title = {Wide-area cooperative storage with {CFS}}, + author = {Frank Dabek and M. Frans Kaashoek and David Karger and Robert Morris and Ion Stoica}, + booktitle = {18th {ACM} {S}ymposium on {O}perating {S}ystems {P}rinciples ({SOSP} '01)}, + year = {2001}, + month = {October}, + address = {Chateau Lake Louise, Banff, Canada}, +} + +@inproceedings{SS03, + title = {Passive Attack Analysis for Connection-Based Anonymity Systems}, + author = {Andrei Serjantov and Peter Sewell}, + booktitle = {Computer Security -- ESORICS 2003}, + publisher = {Springer-Verlag, LNCS 2808}, + year = {2003}, + month = {October}, +} + %note = {\url{http://www.cl.cam.ac.uk/users/aas23/papers_aas/conn_sys.ps}}, + +@Misc{pk-relations, + author = {M. Bellare and A. Desai and D. Pointcheval and P. Rogaway}, + title = {Relations Among Notions of Security for Public-Key Encryption + Schemes}, + howpublished = { + Extended abstract in {\em Advances in Cryptology - CRYPTO '98}, LNCS Vol. 1462. + Springer-Verlag, 1998. + Full version available from \newline \url{http://www-cse.ucsd.edu/users/mihir/}}, +} + + +@InProceedings{mix-acc, + author = {Roger Dingledine and Michael J. Freedman and David + Hopwood and David Molnar}, + title = {{A Reputation System to Increase MIX-net + Reliability}}, + booktitle = {Information Hiding (IH 2001)}, + pages = {126--141}, + year = 2001, + editor = {Ira S. Moskowitz}, + publisher = {Springer-Verlag, LNCS 2137}, +} + %note = {\url{http://www.freehaven.net/papers.html}}, + +@InProceedings{casc-rep, + author = {Roger Dingledine and Paul Syverson}, + title = {{Reliable MIX Cascade Networks through Reputation}}, + booktitle = {Financial Cryptography}, + year = 2002, + editor = {Matt Blaze}, + publisher = {Springer-Verlag, LNCS 2357}, +} + %note = {\newline \url{http://www.freehaven.net/papers.html}}, + +@InProceedings{zhou96certified, + author = {Zhou and Gollmann}, + title = {Certified Electronic Mail}, + booktitle = {{ESORICS: European Symposium on Research in Computer + Security}}, + publisher = {Springer-Verlag, LNCS 1146}, + year = {1996}, + note = {\newline \url{http://citeseer.nj.nec.com/zhou96certified.html}}, +} + +@Misc{realtime-mix, + author = {Anja Jerichow and Jan M\"uller and Andreas Pfitzmann and + Birgit Pfitzmann and Michael Waidner}, + title = {{Real-Time MIXes: A Bandwidth-Efficient Anonymity Protocol}}, + howpublished = {IEEE Journal on Selected Areas in Communications, 1998.}, + note = {\url{http://www.zurich.ibm.com/security/publications/1998.html}}, +} + +@InProceedings{danezis-pets03, + author = {George Danezis}, + title = {Mix-networks with Restricted Routes}, + booktitle = {Privacy Enhancing Technologies (PET 2003)}, + year = 2003, + editor = {Roger Dingledine}, + publisher = {Springer-Verlag LNCS 2760} +} + +@InProceedings{gap-pets03, + author = {Krista Bennett and Christian Grothoff}, + title = {{GAP} -- practical anonymous networking}, + booktitle = {Privacy Enhancing Technologies (PET 2003)}, + year = 2003, + editor = {Roger Dingledine}, + publisher = {Springer-Verlag LNCS 2760} +} + +@Article{hordes-jcs, + author = {Brian Neal Levine and Clay Shields}, + title = {Hordes: A Multicast-Based Protocol for Anonymity}, + journal = {Journal of Computer Security}, + year = 2002, + volume = 10, + number = 3, + pages = {213--240} +} + +@TechReport{herbivore, + author = {Sharad Goel and Mark Robson and Milo Polte and Emin G\"{u}n Sirer}, + title = {Herbivore: A Scalable and Efficient Protocol for Anonymous Communication}, + institution = {Cornell University Computing and Information Science}, + year = 2003, + type = {Technical Report}, + number = {TR2003-1890}, + month = {February} +} + +@InProceedings{p5, + author = {Rob Sherwood and Bobby Bhattacharjee and Aravind Srinivasan}, + title = {$P^5$: A Protocol for Scalable Anonymous Communication}, + booktitle = {IEEE Symposium on Security and Privacy}, + pages = {58--70}, + year = 2002, + publisher = {IEEE CS} +} + +@phdthesis{ian-thesis, + title = {A Pseudonymous Communications Infrastructure for the Internet}, + author = {Ian Goldberg}, + school = {UC Berkeley}, + year = {2000}, + month = {Dec}, +} + +@Article{taz, + author = {Ian Goldberg and David Wagner}, + title = {TAZ Servers and the Rewebber Network: Enabling + Anonymous Publishing on the World Wide Web}, + journal = {First Monday}, + year = 1998, + volume = 3, + number = 4, + month = {August}, + note = {\url{http://www.firstmonday.dk/issues/issue3_4/goldberg/}} +} + +@Misc{tcp-over-tcp-is-bad, + key = {tcp-over-tcp-is-bad}, + title = {Why {TCP} Over {TCP} Is A Bad Idea}, + author = {Olaf Titz}, + note = {\url{http://sites.inka.de/sites/bigred/devel/tcp-tcp.html}} +} + +@inproceedings{wright02, + title = {An Analysis of the Degradation of Anonymous Protocols}, + author = {Matthew Wright and Micah Adler and Brian Neil Levine and Clay Shields}, + booktitle = {{Network and Distributed Security Symposium (NDSS 02)}}, + year = {2002}, + month = {February}, + publisher = {IEEE}, +} + +@inproceedings{wright03, + title = {Defending Anonymous Communication Against Passive Logging Attacks}, + author = {Matthew Wright and Micah Adler and Brian Neil Levine and Clay Shields}, + booktitle = {IEEE Symposium on Security and Privacy}, + pages= {28--41}, + year = {2003}, + month = {May}, + publisher = {IEEE CS}, +} + +@Misc{jap-backdoor, + author={{The AN.ON Project}}, + howpublished={Press release}, + year={2003}, + month={September}, + title={German Police proceeds against anonymity service}, + note={\url{http://www.datenschutzzentrum.de/material/themen/presse/anon-bka_e.htm}} +} + +@article{shsm03, + title = {Using Caching for Browsing Anonymity}, + author = {Anna Shubina and Sean Smith}, + journal = {ACM SIGEcom Exchanges}, + volume = {4}, + number = {2}, + year = {2003}, + month = {Sept}, + www_pdf_url = {http://www.acm.org/sigs/sigecom/exchanges/volume_4_(03)/4.2-Shubina.pdf}, + www_section = {Anonymous communication}, +} + +%%% Local Variables: +%%% mode: latex +%%% TeX-master: "tor-design" +%%% End: diff --git a/doc/design-paper/tor-design.html b/doc/design-paper/tor-design.html new file mode 100644 index 0000000000..a02731f174 --- /dev/null +++ b/doc/design-paper/tor-design.html @@ -0,0 +1,2486 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" + "DTD/xhtml1-transitional.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml"> +<head> +<meta name="GENERATOR" content="TtH 3.59" /> + <style type="text/css"> div.p { margin-top: 7pt;}</style> + <style type="text/css"><!-- + td div.comp { margin-top: -0.6ex; margin-bottom: -1ex;} + td div.comb { margin-top: -0.6ex; margin-bottom: -.6ex;} + td div.hrcomp { line-height: 0.9; margin-top: -0.8ex; margin-bottom: -1ex;} + td div.norm {line-height:normal;} + span.roman {font-family: serif; font-style: normal; font-weight: normal;} + span.overacc2 {position: relative; left: .8em; top: -1.2ex;} + span.overacc1 {position: relative; left: .6em; top: -1.2ex;} --></style> + + +<title> Tor: The Second-Generation Onion Router </title> +</head> +<body> + +<h1 align="center">Tor: The Second-Generation Onion Router </h1> +<div class="p"><!----></div> + +<h3 align="center"> +Roger Dingledine, The Free Haven Project, <tt>arma@freehaven.net</tt><br> +Nick Mathewson, The Free Haven Project, <tt>nickm@freehaven.net</tt><br> +Paul Syverson, Naval Research Lab, <tt>syverson@itd.nrl.navy.mil</tt> </h3> + +<div class="p"><!----></div> + +<div class="p"><!----></div> + +<h2> Abstract</h2> +We present Tor, a circuit-based low-latency anonymous communication +service. This second-generation Onion Routing system addresses limitations +in the original design by adding perfect forward secrecy, congestion +control, directory servers, integrity checking, configurable exit policies, +and a practical design for location-hidden services via rendezvous +points. Tor works on the real-world +Internet, requires no special privileges or kernel modifications, requires +little synchronization or coordination between nodes, and provides a +reasonable tradeoff between anonymity, usability, and efficiency. +We briefly describe our experiences with an international network of +more than 30 nodes. We close with a list of open problems in anonymous communication. + +<div class="p"><!----></div> + +<div class="p"><!----></div> + +<div class="p"><!----></div> + <h2><a name="tth_sEc1"> +1</a> Overview</h2> +<a name="sec:intro"> +</a> + +<div class="p"><!----></div> +Onion Routing is a distributed overlay network designed to anonymize +TCP-based applications like web browsing, secure shell, +and instant messaging. Clients choose a path through the network and +build a <em>circuit</em>, in which each node (or "onion router" or "OR") +in the path knows its predecessor and successor, but no other nodes in +the circuit. Traffic flows down the circuit in fixed-size +<em>cells</em>, which are unwrapped by a symmetric key at each node +(like the layers of an onion) and relayed downstream. The +Onion Routing project published several design and analysis +papers [<a href="#or-ih96" name="CITEor-ih96">27</a>,<a href="#or-jsac98" name="CITEor-jsac98">41</a>,<a href="#or-discex00" name="CITEor-discex00">48</a>,<a href="#or-pet00" name="CITEor-pet00">49</a>]. While a wide area Onion +Routing network was deployed briefly, the only long-running +public implementation was a fragile +proof-of-concept that ran on a single machine. Even this simple deployment +processed connections from over sixty thousand distinct IP addresses from +all over the world at a rate of about fifty thousand per day. +But many critical design and deployment issues were never +resolved, and the design has not been updated in years. Here +we describe Tor, a protocol for asynchronous, loosely federated onion +routers that provides the following improvements over the old Onion +Routing design: + +<div class="p"><!----></div> +<b>Perfect forward secrecy:</b> In the original Onion Routing design, +a single hostile node could record traffic and +later compromise successive nodes in the circuit and force them +to decrypt it. Rather than using a single multiply encrypted data +structure (an <em>onion</em>) to lay each circuit, +Tor now uses an incremental or <em>telescoping</em> path-building design, +where the initiator negotiates session keys with each successive hop in +the circuit. Once these keys are deleted, subsequently compromised nodes +cannot decrypt old traffic. As a side benefit, onion replay detection +is no longer necessary, and the process of building circuits is more +reliable, since the initiator knows when a hop fails and can then try +extending to a new node. + +<div class="p"><!----></div> +<b>Separation of "protocol cleaning" from anonymity:</b> +Onion Routing originally required a separate "application +proxy" for each supported application protocol-most of which were +never written, so many applications were never supported. Tor uses the +standard and near-ubiquitous SOCKS [<a href="#socks4" name="CITEsocks4">32</a>] proxy interface, allowing +us to support most TCP-based programs without modification. Tor now +relies on the filtering features of privacy-enhancing +application-level proxies such as Privoxy [<a href="#privoxy" name="CITEprivoxy">39</a>], without trying +to duplicate those features itself. + +<div class="p"><!----></div> +<b>No mixing, padding, or traffic shaping (yet):</b> Onion +Routing originally called for batching and reordering cells as they arrived, +assumed padding between ORs, and in +later designs added padding between onion proxies (users) and +ORs [<a href="#or-ih96" name="CITEor-ih96">27</a>,<a href="#or-jsac98" name="CITEor-jsac98">41</a>]. Tradeoffs between padding protection +and cost were discussed, and <em>traffic shaping</em> algorithms were +theorized [<a href="#or-pet00" name="CITEor-pet00">49</a>] to provide good security without expensive +padding, but no concrete padding scheme was suggested. +Recent research [<a href="#econymics" name="CITEeconymics">1</a>] +and deployment experience [<a href="#freedom21-security" name="CITEfreedom21-security">4</a>] suggest that this +level of resource use is not practical or economical; and even full +link padding is still vulnerable [<a href="#defensive-dropping" name="CITEdefensive-dropping">33</a>]. Thus, +until we have a proven and convenient design for traffic shaping or +low-latency mixing that improves anonymity against a realistic +adversary, we leave these strategies out. + +<div class="p"><!----></div> +<b>Many TCP streams can share one circuit:</b> Onion Routing originally +built a separate circuit for each +application-level request, but this required +multiple public key operations for every request, and also presented +a threat to anonymity from building so many circuits; see +Section <a href="#sec:maintaining-anonymity">9</a>. Tor multiplexes multiple TCP +streams along each circuit to improve efficiency and anonymity. + +<div class="p"><!----></div> +<b>Leaky-pipe circuit topology:</b> Through in-band signaling +within the circuit, Tor initiators can direct traffic to nodes partway +down the circuit. This novel approach +allows traffic to exit the circuit from the middle-possibly +frustrating traffic shape and volume attacks based on observing the end +of the circuit. (It also allows for long-range padding if +future research shows this to be worthwhile.) + +<div class="p"><!----></div> +<b>Congestion control:</b> Earlier anonymity designs do not +address traffic bottlenecks. Unfortunately, typical approaches to +load balancing and flow control in overlay networks involve inter-node +control communication and global views of traffic. Tor's decentralized +congestion control uses end-to-end acks to maintain anonymity +while allowing nodes at the edges of the network to detect congestion +or flooding and send less data until the congestion subsides. + +<div class="p"><!----></div> +<b>Directory servers:</b> The earlier Onion Routing design +planned to flood state information through the network-an approach +that can be unreliable and complex. Tor takes a simplified view toward distributing this +information. Certain more trusted nodes act as <em>directory +servers</em>: they provide signed directories describing known +routers and their current state. Users periodically download them +via HTTP. + +<div class="p"><!----></div> +<b>Variable exit policies:</b> Tor provides a consistent mechanism +for each node to advertise a policy describing the hosts +and ports to which it will connect. These exit policies are critical +in a volunteer-based distributed infrastructure, because each operator +is comfortable with allowing different types of traffic to exit +from his node. + +<div class="p"><!----></div> +<b>End-to-end integrity checking:</b> The original Onion Routing +design did no integrity checking on data. Any node on the +circuit could change the contents of data cells as they passed by-for +example, to alter a connection request so it would connect +to a different webserver, or to `tag' encrypted traffic and look for +corresponding corrupted traffic at the network edges [<a href="#minion-design" name="CITEminion-design">15</a>]. +Tor hampers these attacks by verifying data integrity before it leaves +the network. + +<div class="p"><!----></div> + +<div class="p"><!----></div> +<b>Rendezvous points and hidden services:</b> +Tor provides an integrated mechanism for responder anonymity via +location-protected servers. Previous Onion Routing designs included +long-lived "reply onions" that could be used to build circuits +to a hidden server, but these reply onions did not provide forward +security, and became useless if any node in the path went down +or rotated its keys. In Tor, clients negotiate <i>rendezvous points</i> +to connect with hidden servers; reply onions are no longer required. + +<div class="p"><!----></div> +Unlike Freedom [<a href="#freedom2-arch" name="CITEfreedom2-arch">8</a>], Tor does not require OS kernel +patches or network stack support. This prevents us from anonymizing +non-TCP protocols, but has greatly helped our portability and +deployability. + +<div class="p"><!----></div> + +<div class="p"><!----></div> +We have implemented all of the above features, including rendezvous +points. Our source code is +available under a free license, and Tor +is not covered by the patent that affected distribution and use of +earlier versions of Onion Routing. +We have deployed a wide-area alpha network +to test the design, to get more experience with usability +and users, and to provide a research platform for experimentation. +As of this writing, the network stands at 32 nodes spread over two continents. + +<div class="p"><!----></div> +We review previous work in Section <a href="#sec:related-work">2</a>, describe +our goals and assumptions in Section <a href="#sec:assumptions">3</a>, +and then address the above list of improvements in +Sections <a href="#sec:design">4</a>, <a href="#sec:rendezvous">5</a>, and <a href="#sec:other-design">6</a>. +We summarize +in Section <a href="#sec:attacks">7</a> how our design stands up to +known attacks, and talk about our early deployment experiences in +Section <a href="#sec:in-the-wild">8</a>. We conclude with a list of open problems in +Section <a href="#sec:maintaining-anonymity">9</a> and future work for the Onion +Routing project in Section <a href="#sec:conclusion">10</a>. + +<div class="p"><!----></div> + +<div class="p"><!----></div> + <h2><a name="tth_sEc2"> +2</a> Related work</h2> +<a name="sec:related-work"> +</a> + +<div class="p"><!----></div> +Modern anonymity systems date to Chaum's <b>Mix-Net</b> +design [<a href="#chaum-mix" name="CITEchaum-mix">10</a>]. Chaum +proposed hiding the correspondence between sender and recipient by +wrapping messages in layers of public-key cryptography, and relaying them +through a path composed of "mixes." Each mix in turn +decrypts, delays, and re-orders messages before relaying them +onward. + +<div class="p"><!----></div> +Subsequent relay-based anonymity designs have diverged in two +main directions. Systems like <b>Babel</b> [<a href="#babel" name="CITEbabel">28</a>], +<b>Mixmaster</b> [<a href="#mixmaster-spec" name="CITEmixmaster-spec">36</a>], +and <b>Mixminion</b> [<a href="#minion-design" name="CITEminion-design">15</a>] have tried +to maximize anonymity at the cost of introducing comparatively large and +variable latencies. Because of this decision, these <em>high-latency</em> +networks resist strong global adversaries, +but introduce too much lag for interactive tasks like web browsing, +Internet chat, or SSH connections. + +<div class="p"><!----></div> +Tor belongs to the second category: <em>low-latency</em> designs that +try to anonymize interactive network traffic. These systems handle +a variety of bidirectional protocols. They also provide more convenient +mail delivery than the high-latency anonymous email +networks, because the remote mail server provides explicit and timely +delivery confirmation. But because these designs typically +involve many packets that must be delivered quickly, it is +difficult for them to prevent an attacker who can eavesdrop both ends of the +communication from correlating the timing and volume +of traffic entering the anonymity network with traffic leaving it [<a href="#SS03" name="CITESS03">45</a>]. +These +protocols are similarly vulnerable to an active adversary who introduces +timing patterns into traffic entering the network and looks +for correlated patterns among exiting traffic. +Although some work has been done to frustrate these attacks, most designs +protect primarily against traffic analysis rather than traffic +confirmation (see Section <a href="#subsec:threat-model">3.1</a>). + +<div class="p"><!----></div> +The simplest low-latency designs are single-hop proxies such as the +<b>Anonymizer</b> [<a href="#anonymizer" name="CITEanonymizer">3</a>]: a single trusted server strips the +data's origin before relaying it. These designs are easy to +analyze, but users must trust the anonymizing proxy. +Concentrating the traffic to this single point increases the anonymity set +(the people a given user is hiding among), but it is vulnerable if the +adversary can observe all traffic entering and leaving the proxy. + +<div class="p"><!----></div> +More complex are distributed-trust, circuit-based anonymizing systems. +In these designs, a user establishes one or more medium-term bidirectional +end-to-end circuits, and tunnels data in fixed-size cells. +Establishing circuits is computationally expensive and typically +requires public-key +cryptography, whereas relaying cells is comparatively inexpensive and +typically requires only symmetric encryption. +Because a circuit crosses several servers, and each server only knows +the adjacent servers in the circuit, no single server can link a +user to her communication partners. + +<div class="p"><!----></div> +The <b>Java Anon Proxy</b> (also known as JAP or Web MIXes) uses fixed shared +routes known as <em>cascades</em>. As with a single-hop proxy, this +approach aggregates users into larger anonymity sets, but again an +attacker only needs to observe both ends of the cascade to bridge all +the system's traffic. The Java Anon Proxy's design +calls for padding between end users and the head of the +cascade [<a href="#web-mix" name="CITEweb-mix">7</a>]. However, it is not demonstrated whether the current +implementation's padding policy improves anonymity. + +<div class="p"><!----></div> +<b>PipeNet</b> [<a href="#back01" name="CITEback01">5</a>,<a href="#pipenet" name="CITEpipenet">12</a>], another low-latency design proposed +around the same time as Onion Routing, gave +stronger anonymity but allowed a single user to shut +down the network by not sending. Systems like <b>ISDN +mixes</b> [<a href="#isdn-mixes" name="CITEisdn-mixes">38</a>] were designed for other environments with +different assumptions. + +<div class="p"><!----></div> +In P2P designs like <b>Tarzan</b> [<a href="#tarzan:ccs02" name="CITEtarzan:ccs02">24</a>] and +<b>MorphMix</b> [<a href="#morphmix:fc04" name="CITEmorphmix:fc04">43</a>], all participants both generate +traffic and relay traffic for others. These systems aim to conceal +whether a given peer originated a request +or just relayed it from another peer. While Tarzan and MorphMix use +layered encryption as above, <b>Crowds</b> [<a href="#crowds-tissec" name="CITEcrowds-tissec">42</a>] simply assumes +an adversary who cannot observe the initiator: it uses no public-key +encryption, so any node on a circuit can read users' traffic. + +<div class="p"><!----></div> +<b>Hordes</b> [<a href="#hordes-jcs" name="CITEhordes-jcs">34</a>] is based on Crowds but also uses multicast +responses to hide the initiator. <b>Herbivore</b> [<a href="#herbivore" name="CITEherbivore">25</a>] and +<b>P</b><sup><b>5</b></sup> [<a href="#p5" name="CITEp5">46</a>] go even further, requiring broadcast. +These systems are designed primarily for communication among peers, +although Herbivore users can make external connections by +requesting a peer to serve as a proxy. + +<div class="p"><!----></div> +Systems like <b>Freedom</b> and the original Onion Routing build circuits +all at once, using a layered "onion" of public-key encrypted messages, +each layer of which provides session keys and the address of the +next server in the circuit. Tor as described herein, Tarzan, MorphMix, +<b>Cebolla</b> [<a href="#cebolla" name="CITEcebolla">9</a>], and Rennhard's <b>Anonymity Network</b> [<a href="#anonnet" name="CITEanonnet">44</a>] +build circuits +in stages, extending them one hop at a time. +Section <a href="#subsubsec:constructing-a-circuit">4.2</a> describes how this +approach enables perfect forward secrecy. + +<div class="p"><!----></div> +Circuit-based designs must choose which protocol layer +to anonymize. They may intercept IP packets directly, and +relay them whole (stripping the source address) along the +circuit [<a href="#freedom2-arch" name="CITEfreedom2-arch">8</a>,<a href="#tarzan:ccs02" name="CITEtarzan:ccs02">24</a>]. Like +Tor, they may accept TCP streams and relay the data in those streams, +ignoring the breakdown of that data into TCP +segments [<a href="#morphmix:fc04" name="CITEmorphmix:fc04">43</a>,<a href="#anonnet" name="CITEanonnet">44</a>]. Finally, like Crowds, they may accept +application-level protocols such as HTTP and relay the application +requests themselves. +Making this protocol-layer decision requires a compromise between flexibility +and anonymity. For example, a system that understands HTTP +can strip +identifying information from requests, can take advantage of caching +to limit the number of requests that leave the network, and can batch +or encode requests to minimize the number of connections. +On the other hand, an IP-level anonymizer can handle nearly any protocol, +even ones unforeseen by its designers (though these systems require +kernel-level modifications to some operating systems, and so are more +complex and less portable). TCP-level anonymity networks like Tor present +a middle approach: they are application neutral (so long as the +application supports, or can be tunneled across, TCP), but by treating +application connections as data streams rather than raw TCP packets, +they avoid the inefficiencies of tunneling TCP over +TCP. + +<div class="p"><!----></div> +Distributed-trust anonymizing systems need to prevent attackers from +adding too many servers and thus compromising user paths. +Tor relies on a small set of well-known directory servers, run by +independent parties, to decide which nodes can +join. Tarzan and MorphMix allow unknown users to run servers, and use +a limited resource (like IP addresses) to prevent an attacker from +controlling too much of the network. Crowds suggests requiring +written, notarized requests from potential crowd members. + +<div class="p"><!----></div> +Anonymous communication is essential for censorship-resistant +systems like Eternity [<a href="#eternity" name="CITEeternity">2</a>], Free Haven [<a href="#freehaven-berk" name="CITEfreehaven-berk">19</a>], +Publius [<a href="#publius" name="CITEpublius">53</a>], and Tangler [<a href="#tangler" name="CITEtangler">52</a>]. Tor's rendezvous +points enable connections between mutually anonymous entities; they +are a building block for location-hidden servers, which are needed by +Eternity and Free Haven. + +<div class="p"><!----></div> + +<div class="p"><!----></div> + <h2><a name="tth_sEc3"> +3</a> Design goals and assumptions</h2> +<a name="sec:assumptions"> +</a> + +<div class="p"><!----></div> +<font size="+1"><b>Goals</b></font><br /> +Like other low-latency anonymity designs, Tor seeks to frustrate +attackers from linking communication partners, or from linking +multiple communications to or from a single user. Within this +main goal, however, several considerations have directed +Tor's evolution. + +<div class="p"><!----></div> +<b>Deployability:</b> The design must be deployed and used in the +real world. Thus it +must not be expensive to run (for example, by requiring more bandwidth +than volunteers are willing to provide); must not place a heavy +liability burden on operators (for example, by allowing attackers to +implicate onion routers in illegal activities); and must not be +difficult or expensive to implement (for example, by requiring kernel +patches, or separate proxies for every protocol). We also cannot +require non-anonymous parties (such as websites) +to run our software. (Our rendezvous point design does not meet +this goal for non-anonymous users talking to hidden servers, +however; see Section <a href="#sec:rendezvous">5</a>.) + +<div class="p"><!----></div> +<b>Usability:</b> A hard-to-use system has fewer users-and because +anonymity systems hide users among users, a system with fewer users +provides less anonymity. Usability is thus not only a convenience: +it is a security requirement [<a href="#econymics" name="CITEeconymics">1</a>,<a href="#back01" name="CITEback01">5</a>]. Tor should +therefore not +require modifying familiar applications; should not introduce prohibitive +delays; +and should require as few configuration decisions +as possible. Finally, Tor should be easily implementable on all common +platforms; we cannot require users to change their operating system +to be anonymous. (Tor currently runs on Win32, Linux, +Solaris, BSD-style Unix, MacOS X, and probably others.) + +<div class="p"><!----></div> +<b>Flexibility:</b> The protocol must be flexible and well-specified, +so Tor can serve as a test-bed for future research. +Many of the open problems in low-latency anonymity +networks, such as generating dummy traffic or preventing Sybil +attacks [<a href="#sybil" name="CITEsybil">22</a>], may be solvable independently from the issues +solved by +Tor. Hopefully future systems will not need to reinvent Tor's design. + +<div class="p"><!----></div> +<b>Simple design:</b> The protocol's design and security +parameters must be well-understood. Additional features impose implementation +and complexity costs; adding unproven techniques to the design threatens +deployability, readability, and ease of security analysis. Tor aims to +deploy a simple and stable system that integrates the best accepted +approaches to protecting anonymity.<br /> + +<div class="p"><!----></div> +<font size="+1"><b>Non-goals</b></font><a name="subsec:non-goals"> +</a><br /> +In favoring simple, deployable designs, we have explicitly deferred +several possible goals, either because they are solved elsewhere, or because +they are not yet solved. + +<div class="p"><!----></div> +<b>Not peer-to-peer:</b> Tarzan and MorphMix aim to scale to completely +decentralized peer-to-peer environments with thousands of short-lived +servers, many of which may be controlled by an adversary. This approach +is appealing, but still has many open +problems [<a href="#tarzan:ccs02" name="CITEtarzan:ccs02">24</a>,<a href="#morphmix:fc04" name="CITEmorphmix:fc04">43</a>]. + +<div class="p"><!----></div> +<b>Not secure against end-to-end attacks:</b> Tor does not claim +to completely solve end-to-end timing or intersection +attacks. Some approaches, such as having users run their own onion routers, +may help; +see Section <a href="#sec:maintaining-anonymity">9</a> for more discussion. + +<div class="p"><!----></div> +<b>No protocol normalization:</b> Tor does not provide <em>protocol +normalization</em> like Privoxy or the Anonymizer. If senders want anonymity from +responders while using complex and variable +protocols like HTTP, Tor must be layered with a filtering proxy such +as Privoxy to hide differences between clients, and expunge protocol +features that leak identity. +Note that by this separation Tor can also provide services that +are anonymous to the network yet authenticated to the responder, like +SSH. Similarly, Tor does not integrate +tunneling for non-stream-based protocols like UDP; this must be +provided by an external service if appropriate. + +<div class="p"><!----></div> +<b>Not steganographic:</b> Tor does not try to conceal who is connected +to the network. + +<div class="p"><!----></div> + <h3><a name="tth_sEc3.1"> +3.1</a> Threat Model</h3> +<a name="subsec:threat-model"> +</a> + +<div class="p"><!----></div> +A global passive adversary is the most commonly assumed threat when +analyzing theoretical anonymity designs. But like all practical +low-latency systems, Tor does not protect against such a strong +adversary. Instead, we assume an adversary who can observe some fraction +of network traffic; who can generate, modify, delete, or delay +traffic; who can operate onion routers of his own; and who can +compromise some fraction of the onion routers. + +<div class="p"><!----></div> +In low-latency anonymity systems that use layered encryption, the +adversary's typical goal is to observe both the initiator and the +responder. By observing both ends, passive attackers can confirm a +suspicion that Alice is +talking to Bob if the timing and volume patterns of the traffic on the +connection are distinct enough; active attackers can induce timing +signatures on the traffic to force distinct patterns. Rather +than focusing on these <em>traffic confirmation</em> attacks, +we aim to prevent <em>traffic +analysis</em> attacks, where the adversary uses traffic patterns to learn +which points in the network he should attack. + +<div class="p"><!----></div> +Our adversary might try to link an initiator Alice with her +communication partners, or try to build a profile of Alice's +behavior. He might mount passive attacks by observing the network edges +and correlating traffic entering and leaving the network-by +relationships in packet timing, volume, or externally visible +user-selected +options. The adversary can also mount active attacks by compromising +routers or keys; by replaying traffic; by selectively denying service +to trustworthy routers to move users to +compromised routers, or denying service to users to see if traffic +elsewhere in the +network stops; or by introducing patterns into traffic that can later be +detected. The adversary might subvert the directory servers to give users +differing views of network state. Additionally, he can try to decrease +the network's reliability by attacking nodes or by performing antisocial +activities from reliable nodes and trying to get them taken down-making +the network unreliable flushes users to other less anonymous +systems, where they may be easier to attack. We summarize +in Section <a href="#sec:attacks">7</a> how well the Tor design defends against +each of these attacks. + +<div class="p"><!----></div> + +<div class="p"><!----></div> + <h2><a name="tth_sEc4"> +4</a> The Tor Design</h2> +<a name="sec:design"> +</a> + +<div class="p"><!----></div> +The Tor network is an overlay network; each onion router (OR) +runs as a normal +user-level process without any special privileges. +Each onion router maintains a TLS [<a href="#TLS" name="CITETLS">17</a>] +connection to every other onion router. +Each user +runs local software called an onion proxy (OP) to fetch directories, +establish circuits across the network, +and handle connections from user applications. These onion proxies accept +TCP streams and multiplex them across the circuits. The onion +router on the other side +of the circuit connects to the requested destinations +and relays data. + +<div class="p"><!----></div> +Each onion router maintains a long-term identity key and a short-term +onion key. The identity +key is used to sign TLS certificates, to sign the OR's <em>router +descriptor</em> (a summary of its keys, address, bandwidth, exit policy, +and so on), and (by directory servers) to sign directories. The onion key is used to decrypt requests +from users to set up a circuit and negotiate ephemeral keys. +The TLS protocol also establishes a short-term link key when communicating +between ORs. Short-term keys are rotated periodically and +independently, to limit the impact of key compromise. + +<div class="p"><!----></div> +Section <a href="#subsec:cells">4.1</a> presents the fixed-size +<em>cells</em> that are the unit of communication in Tor. We describe +in Section <a href="#subsec:circuits">4.2</a> how circuits are +built, extended, truncated, and destroyed. Section <a href="#subsec:tcp">4.3</a> +describes how TCP streams are routed through the network. We address +integrity checking in Section <a href="#subsec:integrity-checking">4.4</a>, +and resource limiting in Section <a href="#subsec:rate-limit">4.5</a>. +Finally, +Section <a href="#subsec:congestion">4.6</a> talks about congestion control and +fairness issues. + +<div class="p"><!----></div> + <h3><a name="tth_sEc4.1"> +4.1</a> Cells</h3> +<a name="subsec:cells"> +</a> + +<div class="p"><!----></div> +Onion routers communicate with one another, and with users' OPs, via +TLS connections with ephemeral keys. Using TLS conceals the data on +the connection with perfect forward secrecy, and prevents an attacker +from modifying data on the wire or impersonating an OR. + +<div class="p"><!----></div> +Traffic passes along these connections in fixed-size cells. Each cell +is 512 bytes, and consists of a header and a payload. The header includes a circuit +identifier (circID) that specifies which circuit the cell refers to +(many circuits can be multiplexed over the single TLS connection), and +a command to describe what to do with the cell's payload. (Circuit +identifiers are connection-specific: each circuit has a different +circID on each OP/OR or OR/OR connection it traverses.) +Based on their command, cells are either <em>control</em> cells, which are +always interpreted by the node that receives them, or <em>relay</em> cells, +which carry end-to-end stream data. The control cell commands are: +<em>padding</em> (currently used for keepalive, but also usable for link +padding); <em>create</em> or <em>created</em> (used to set up a new circuit); +and <em>destroy</em> (to tear down a circuit). + +<div class="p"><!----></div> +Relay cells have an additional header (the relay header) at the front +of the payload, containing a streamID (stream identifier: many streams can +be multiplexed over a circuit); an end-to-end checksum for integrity +checking; the length of the relay payload; and a relay command. +The entire contents of the relay header and the relay cell payload +are encrypted or decrypted together as the relay cell moves along the +circuit, using the 128-bit AES cipher in counter mode to generate a +cipher stream. The relay commands are: <em>relay +data</em> (for data flowing down the stream), <em>relay begin</em> (to open a +stream), <em>relay end</em> (to close a stream cleanly), <em>relay +teardown</em> (to close a broken stream), <em>relay connected</em> +(to notify the OP that a relay begin has succeeded), <em>relay +extend</em> and <em>relay extended</em> (to extend the circuit by a hop, +and to acknowledge), <em>relay truncate</em> and <em>relay truncated</em> +(to tear down only part of the circuit, and to acknowledge), <em>relay +sendme</em> (used for congestion control), and <em>relay drop</em> (used to +implement long-range dummies). +We give a visual overview of cell structure plus the details of relay +cell structure, and then describe each of these cell types and commands +in more detail below. + +<div class="p"><!----></div> + +<div class="p"><!----></div> + +<div class="p"><!----></div> +<a name="tth_fIg1"> +</a> <center><img src="cell-struct.png" alt="cell-struct.png" /> +</center> +<div class="p"><!----></div> + <h3><a name="tth_sEc4.2"> +4.2</a> Circuits and streams</h3> +<a name="subsec:circuits"> +</a> + +<div class="p"><!----></div> +Onion Routing originally built one circuit for each +TCP stream. Because building a circuit can take several tenths of a +second (due to public-key cryptography and network latency), +this design imposed high costs on applications like web browsing that +open many TCP streams. + +<div class="p"><!----></div> +In Tor, each circuit can be shared by many TCP streams. To avoid +delays, users construct circuits preemptively. To limit linkability +among their streams, users' OPs build a new circuit +periodically if the previous ones have been used, +and expire old used circuits that no longer have any open streams. +OPs consider rotating to a new circuit once a minute: thus +even heavy users spend negligible time +building circuits, but a limited number of requests can be linked +to each other through a given exit node. Also, because circuits are built +in the background, OPs can recover from failed circuit creation +without harming user experience.<br /> + +<div class="p"><!----></div> + +<div class="p"><!----></div> +<a name="tth_fIg1"> +</a> <center><img src="interaction.png" alt="interaction.png" /> + +<center>Figure 1: Alice builds a two-hop circuit and begins fetching a web page.</center> +<a name="fig:interaction"> +</a> +</center> +<div class="p"><!----></div> +<font size="+1"><b>Constructing a circuit</b></font><a name="subsubsec:constructing-a-circuit"> +</a><br /> +A user's OP constructs circuits incrementally, negotiating a +symmetric key with each OR on the circuit, one hop at a time. To begin +creating a new circuit, the OP (call her Alice) sends a +<em>create</em> cell to the first node in her chosen path (call him Bob). +(She chooses a new +circID C<sub>AB</sub> not currently used on the connection from her to Bob.) +The <em>create</em> cell's +payload contains the first half of the Diffie-Hellman handshake +(g<sup>x</sup>), encrypted to the onion key of the OR (call him Bob). Bob +responds with a <em>created</em> cell containing g<sup>y</sup> +along with a hash of the negotiated key K=g<sup>xy</sup>. + +<div class="p"><!----></div> +Once the circuit has been established, Alice and Bob can send one +another relay cells encrypted with the negotiated +key.<a href="#tthFtNtAAB" name="tthFrefAAB"><sup>1</sup></a> More detail is given in +the next section. + +<div class="p"><!----></div> +To extend the circuit further, Alice sends a <em>relay extend</em> cell +to Bob, specifying the address of the next OR (call her Carol), and +an encrypted g<sup>x<sub>2</sub></sup> for her. Bob copies the half-handshake into a +<em>create</em> cell, and passes it to Carol to extend the circuit. +(Bob chooses a new circID C<sub>BC</sub> not currently used on the connection +between him and Carol. Alice never needs to know this circID; only Bob +associates C<sub>AB</sub> on his connection with Alice to C<sub>BC</sub> on +his connection with Carol.) +When Carol responds with a <em>created</em> cell, Bob wraps the payload +into a <em>relay extended</em> cell and passes it back to Alice. Now +the circuit is extended to Carol, and Alice and Carol share a common key +K<sub>2</sub> = g<sup>x<sub>2</sub> y<sub>2</sub></sup>. + +<div class="p"><!----></div> +To extend the circuit to a third node or beyond, Alice +proceeds as above, always telling the last node in the circuit to +extend one hop further. + +<div class="p"><!----></div> +This circuit-level handshake protocol achieves unilateral entity +authentication (Alice knows she's handshaking with the OR, but +the OR doesn't care who is opening the circuit-Alice uses no public key +and remains anonymous) and unilateral key authentication +(Alice and the OR agree on a key, and Alice knows only the OR learns +it). It also achieves forward +secrecy and key freshness. More formally, the protocol is as follows +(where E<sub>PK<sub>Bob</sub></sub>(·) is encryption with Bob's public key, +H is a secure hash function, and <font face="symbol">|</font +> is concatenation): + +<div class="p"><!----></div> +<a name="tth_tAb1"> +</a> +<table> +<tr><td align="right">Alice </td><td align="center">-> </td><td align="center">Bob </td><td>: E<sub>PK<sub>Bob</sub></sub>(g<sup>x</sup>) </td></tr> +<tr><td align="right">Bob </td><td align="center">-> </td><td align="center">Alice </td><td>: g<sup>y</sup>, H(K <font face="symbol">|</font +> "<span class="roman">handshake</span>") +</td></tr></table> + + +<div class="p"><!----></div> + In the second step, Bob proves that it was he who received g<sup>x</sup>, +and who chose y. We use PK encryption in the first step +(rather than, say, using the first two steps of STS, which has a +signature in the second step) because a single cell is too small to +hold both a public key and a signature. Preliminary analysis with the +NRL protocol analyzer [<a href="#meadows96" name="CITEmeadows96">35</a>] shows this protocol to be +secure (including perfect forward secrecy) under the +traditional Dolev-Yao model.<br /> + +<div class="p"><!----></div> +<font size="+1"><b>Relay cells</b></font><br /> +Once Alice has established the circuit (so she shares keys with each +OR on the circuit), she can send relay cells. +Upon receiving a relay +cell, an OR looks up the corresponding circuit, and decrypts the relay +header and payload with the session key for that circuit. +If the cell is headed away from Alice the OR then checks whether the +decrypted cell has a valid digest (as an optimization, the first +two bytes of the integrity check are zero, so in most cases we can avoid +computing the hash). +If valid, it accepts the relay cell and processes it as described +below. Otherwise, +the OR looks up the circID and OR for the +next step in the circuit, replaces the circID as appropriate, and +sends the decrypted relay cell to the next OR. (If the OR at the end +of the circuit receives an unrecognized relay cell, an error has +occurred, and the circuit is torn down.) + +<div class="p"><!----></div> +OPs treat incoming relay cells similarly: they iteratively unwrap the +relay header and payload with the session keys shared with each +OR on the circuit, from the closest to farthest. +If at any stage the digest is valid, the cell must have +originated at the OR whose encryption has just been removed. + +<div class="p"><!----></div> +To construct a relay cell addressed to a given OR, Alice assigns the +digest, and then iteratively +encrypts the cell payload (that is, the relay header and payload) with +the symmetric key of each hop up to that OR. Because the digest is +encrypted to a different value at each step, only at the targeted OR +will it have a meaningful value.<a href="#tthFtNtAAC" name="tthFrefAAC"><sup>2</sup></a> +This <em>leaky pipe</em> circuit topology +allows Alice's streams to exit at different ORs on a single circuit. +Alice may choose different exit points because of their exit policies, +or to keep the ORs from knowing that two streams +originate from the same person. + +<div class="p"><!----></div> +When an OR later replies to Alice with a relay cell, it +encrypts the cell's relay header and payload with the single key it +shares with Alice, and sends the cell back toward Alice along the +circuit. Subsequent ORs add further layers of encryption as they +relay the cell back to Alice. + +<div class="p"><!----></div> +To tear down a circuit, Alice sends a <em>destroy</em> control +cell. Each OR in the circuit receives the <em>destroy</em> cell, closes +all streams on that circuit, and passes a new <em>destroy</em> cell +forward. But just as circuits are built incrementally, they can also +be torn down incrementally: Alice can send a <em>relay +truncate</em> cell to a single OR on a circuit. That OR then sends a +<em>destroy</em> cell forward, and acknowledges with a +<em>relay truncated</em> cell. Alice can then extend the circuit to +different nodes, without signaling to the intermediate nodes (or +a limited observer) that she has changed her circuit. +Similarly, if a node on the circuit goes down, the adjacent +node can send a <em>relay truncated</em> cell back to Alice. Thus the +"break a node and see which circuits go down" +attack [<a href="#freedom21-security" name="CITEfreedom21-security">4</a>] is weakened. + +<div class="p"><!----></div> + <h3><a name="tth_sEc4.3"> +4.3</a> Opening and closing streams</h3> +<a name="subsec:tcp"> +</a> + +<div class="p"><!----></div> +When Alice's application wants a TCP connection to a given +address and port, it asks the OP (via SOCKS) to make the +connection. The OP chooses the newest open circuit (or creates one if +needed), and chooses a suitable OR on that circuit to be the +exit node (usually the last node, but maybe others due to exit policy +conflicts; see Section <a href="#subsec:exitpolicies">6.2</a>.) The OP then opens +the stream by sending a <em>relay begin</em> cell to the exit node, +using a new random streamID. Once the +exit node connects to the remote host, it responds +with a <em>relay connected</em> cell. Upon receipt, the OP sends a +SOCKS reply to notify the application of its success. The OP +now accepts data from the application's TCP stream, packaging it into +<em>relay data</em> cells and sending those cells along the circuit to +the chosen OR. + +<div class="p"><!----></div> +There's a catch to using SOCKS, however-some applications pass the +alphanumeric hostname to the Tor client, while others resolve it into +an IP address first and then pass the IP address to the Tor client. If +the application does DNS resolution first, Alice thereby reveals her +destination to the remote DNS server, rather than sending the hostname +through the Tor network to be resolved at the far end. Common applications +like Mozilla and SSH have this flaw. + +<div class="p"><!----></div> +With Mozilla, the flaw is easy to address: the filtering HTTP +proxy called Privoxy gives a hostname to the Tor client, so Alice's +computer never does DNS resolution. +But a portable general solution, such as is needed for +SSH, is +an open problem. Modifying or replacing the local nameserver +can be invasive, brittle, and unportable. Forcing the resolver +library to prefer TCP rather than UDP is hard, and also has +portability problems. Dynamically intercepting system calls to the +resolver library seems a promising direction. We could also provide +a tool similar to <em>dig</em> to perform a private lookup through the +Tor network. Currently, we encourage the use of privacy-aware proxies +like Privoxy wherever possible. + +<div class="p"><!----></div> +Closing a Tor stream is analogous to closing a TCP stream: it uses a +two-step handshake for normal operation, or a one-step handshake for +errors. If the stream closes abnormally, the adjacent node simply sends a +<em>relay teardown</em> cell. If the stream closes normally, the node sends +a <em>relay end</em> cell down the circuit, and the other side responds with +its own <em>relay end</em> cell. Because +all relay cells use layered encryption, only the destination OR knows +that a given relay cell is a request to close a stream. This two-step +handshake allows Tor to support TCP-based applications that use half-closed +connections. + +<div class="p"><!----></div> + <h3><a name="tth_sEc4.4"> +4.4</a> Integrity checking on streams</h3> +<a name="subsec:integrity-checking"> +</a> + +<div class="p"><!----></div> +Because the old Onion Routing design used a stream cipher without integrity +checking, traffic was +vulnerable to a malleability attack: though the attacker could not +decrypt cells, any changes to encrypted data +would create corresponding changes to the data leaving the network. +This weakness allowed an adversary who could guess the encrypted content +to change a padding cell to a destroy +cell; change the destination address in a <em>relay begin</em> cell to the +adversary's webserver; or change an FTP command from +<tt>dir</tt> to <tt>rm *</tt>. (Even an external +adversary could do this, because the link encryption similarly used a +stream cipher.) + +<div class="p"><!----></div> +Because Tor uses TLS on its links, external adversaries cannot modify +data. Addressing the insider malleability attack, however, is +more complex. + +<div class="p"><!----></div> +We could do integrity checking of the relay cells at each hop, either +by including hashes or by using an authenticating cipher mode like +EAX [<a href="#eax" name="CITEeax">6</a>], but there are some problems. First, these approaches +impose a message-expansion overhead at each hop, and so we would have to +either leak the path length or waste bytes by padding to a maximum +path length. Second, these solutions can only verify traffic coming +from Alice: ORs would not be able to produce suitable hashes for +the intermediate hops, since the ORs on a circuit do not know the +other ORs' session keys. Third, we have already accepted that our design +is vulnerable to end-to-end timing attacks; so tagging attacks performed +within the circuit provide no additional information to the attacker. + +<div class="p"><!----></div> +Thus, we check integrity only at the edges of each stream. (Remember that +in our leaky-pipe circuit topology, a stream's edge could be any hop +in the circuit.) When Alice +negotiates a key with a new hop, they each initialize a SHA-1 +digest with a derivative of that key, +thus beginning with randomness that only the two of them know. +Then they each incrementally add to the SHA-1 digest the contents of +all relay cells they create, and include with each relay cell the +first four bytes of the current digest. Each also keeps a SHA-1 +digest of data received, to verify that the received hashes are correct. + +<div class="p"><!----></div> +To be sure of removing or modifying a cell, the attacker must be able +to deduce the current digest state (which depends on all +traffic between Alice and Bob, starting with their negotiated key). +Attacks on SHA-1 where the adversary can incrementally add to a hash +to produce a new valid hash don't work, because all hashes are +end-to-end encrypted across the circuit. The computational overhead +of computing the digests is minimal compared to doing the AES +encryption performed at each hop of the circuit. We use only four +bytes per cell to minimize overhead; the chance that an adversary will +correctly guess a valid hash +is +acceptably low, given that the OP or OR tear down the circuit if they +receive a bad hash. + +<div class="p"><!----></div> + <h3><a name="tth_sEc4.5"> +4.5</a> Rate limiting and fairness</h3> +<a name="subsec:rate-limit"> +</a> + +<div class="p"><!----></div> +Volunteers are more willing to run services that can limit +their bandwidth usage. To accommodate them, Tor servers use a +token bucket approach [<a href="#tannenbaum96" name="CITEtannenbaum96">50</a>] to +enforce a long-term average rate of incoming bytes, while still +permitting short-term bursts above the allowed bandwidth. + +<div class="p"><!----></div> + +<div class="p"><!----></div> +Because the Tor protocol outputs about the same number of bytes as it +takes in, it is sufficient in practice to limit only incoming bytes. +With TCP streams, however, the correspondence is not one-to-one: +relaying a single incoming byte can require an entire 512-byte cell. +(We can't just wait for more bytes, because the local application may +be awaiting a reply.) Therefore, we treat this case as if the entire +cell size had been read, regardless of the cell's fullness. + +<div class="p"><!----></div> +Further, inspired by Rennhard et al's design in [<a href="#anonnet" name="CITEanonnet">44</a>], a +circuit's edges can heuristically distinguish interactive streams from bulk +streams by comparing the frequency with which they supply cells. We can +provide good latency for interactive streams by giving them preferential +service, while still giving good overall throughput to the bulk +streams. Such preferential treatment presents a possible end-to-end +attack, but an adversary observing both +ends of the stream can already learn this information through timing +attacks. + +<div class="p"><!----></div> + <h3><a name="tth_sEc4.6"> +4.6</a> Congestion control</h3> +<a name="subsec:congestion"> +</a> + +<div class="p"><!----></div> +Even with bandwidth rate limiting, we still need to worry about +congestion, either accidental or intentional. If enough users choose the +same OR-to-OR connection for their circuits, that connection can become +saturated. For example, an attacker could send a large file +through the Tor network to a webserver he runs, and then +refuse to read any of the bytes at the webserver end of the +circuit. Without some congestion control mechanism, these bottlenecks +can propagate back through the entire network. We don't need to +reimplement full TCP windows (with sequence numbers, +the ability to drop cells when we're full and retransmit later, and so +on), +because TCP already guarantees in-order delivery of each +cell. +We describe our response below. + +<div class="p"><!----></div> +<b>Circuit-level throttling:</b> +To control a circuit's bandwidth usage, each OR keeps track of two +windows. The <em>packaging window</em> tracks how many relay data cells the OR is +allowed to package (from incoming TCP streams) for transmission back to the OP, +and the <em>delivery window</em> tracks how many relay data cells it is willing +to deliver to TCP streams outside the network. Each window is initialized +(say, to 1000 data cells). When a data cell is packaged or delivered, +the appropriate window is decremented. When an OR has received enough +data cells (currently 100), it sends a <em>relay sendme</em> cell towards the OP, +with streamID zero. When an OR receives a <em>relay sendme</em> cell with +streamID zero, it increments its packaging window. Either of these cells +increments the corresponding window by 100. If the packaging window +reaches 0, the OR stops reading from TCP connections for all streams +on the corresponding circuit, and sends no more relay data cells until +receiving a <em>relay sendme</em> cell. + +<div class="p"><!----></div> +The OP behaves identically, except that it must track a packaging window +and a delivery window for every OR in the circuit. If a packaging window +reaches 0, it stops reading from streams destined for that OR. + +<div class="p"><!----></div> +<b>Stream-level throttling</b>: +The stream-level congestion control mechanism is similar to the +circuit-level mechanism. ORs and OPs use <em>relay sendme</em> cells +to implement end-to-end flow control for individual streams across +circuits. Each stream begins with a packaging window (currently 500 cells), +and increments the window by a fixed value (50) upon receiving a <em>relay +sendme</em> cell. Rather than always returning a <em>relay sendme</em> cell as soon +as enough cells have arrived, the stream-level congestion control also +has to check whether data has been successfully flushed onto the TCP +stream; it sends the <em>relay sendme</em> cell only when the number of bytes pending +to be flushed is under some threshold (currently 10 cells' worth). + +<div class="p"><!----></div> + +<div class="p"><!----></div> +These arbitrarily chosen parameters seem to give tolerable throughput +and delay; see Section <a href="#sec:in-the-wild">8</a>. + +<div class="p"><!----></div> + <h2><a name="tth_sEc5"> +5</a> Rendezvous Points and hidden services</h2> +<a name="sec:rendezvous"> +</a> + +<div class="p"><!----></div> +Rendezvous points are a building block for <em>location-hidden +services</em> (also known as <em>responder anonymity</em>) in the Tor +network. Location-hidden services allow Bob to offer a TCP +service, such as a webserver, without revealing his IP address. +This type of anonymity protects against distributed DoS attacks: +attackers are forced to attack the onion routing network +because they do not know Bob's IP address. + +<div class="p"><!----></div> +Our design for location-hidden servers has the following goals. +<b>Access-control:</b> Bob needs a way to filter incoming requests, +so an attacker cannot flood Bob simply by making many connections to him. +<b>Robustness:</b> Bob should be able to maintain a long-term pseudonymous +identity even in the presence of router failure. Bob's service must +not be tied to a single OR, and Bob must be able to migrate his service +across ORs. <b>Smear-resistance:</b> +A social attacker +should not be able to "frame" a rendezvous router by +offering an illegal or disreputable location-hidden service and +making observers believe the router created that service. +<b>Application-transparency:</b> Although we require users +to run special software to access location-hidden servers, we must not +require them to modify their applications. + +<div class="p"><!----></div> +We provide location-hiding for Bob by allowing him to advertise +several onion routers (his <em>introduction points</em>) as contact +points. He may do this on any robust efficient +key-value lookup system with authenticated updates, such as a +distributed hash table (DHT) like CFS [<a href="#cfs:sosp01" name="CITEcfs:sosp01">11</a>].<a href="#tthFtNtAAD" name="tthFrefAAD"><sup>3</sup></a> Alice, the client, chooses an OR as her +<em>rendezvous point</em>. She connects to one of Bob's introduction +points, informs him of her rendezvous point, and then waits for him +to connect to the rendezvous point. This extra level of indirection +helps Bob's introduction points avoid problems associated with serving +unpopular files directly (for example, if Bob serves +material that the introduction point's community finds objectionable, +or if Bob's service tends to get attacked by network vandals). +The extra level of indirection also allows Bob to respond to some requests +and ignore others. + +<div class="p"><!----></div> + <h3><a name="tth_sEc5.1"> +5.1</a> Rendezvous points in Tor</h3> + +<div class="p"><!----></div> +The following steps are +performed on behalf of Alice and Bob by their local OPs; +application integration is described more fully below. + +<div class="p"><!----></div> + +<dl compact="compact"> + + <dt><b></b></dt> + <dd><li>Bob generates a long-term public key pair to identify his service.</dd> + <dt><b></b></dt> + <dd><li>Bob chooses some introduction points, and advertises them on + the lookup service, signing the advertisement with his public key. He + can add more later.</dd> + <dt><b></b></dt> + <dd><li>Bob builds a circuit to each of his introduction points, and tells + them to wait for requests.</dd> + <dt><b></b></dt> + <dd><li>Alice learns about Bob's service out of band (perhaps Bob told her, + or she found it on a website). She retrieves the details of Bob's + service from the lookup service. If Alice wants to access Bob's + service anonymously, she must connect to the lookup service via Tor.</dd> + <dt><b></b></dt> + <dd><li>Alice chooses an OR as the rendezvous point (RP) for her connection to + Bob's service. She builds a circuit to the RP, and gives it a + randomly chosen "rendezvous cookie" to recognize Bob.</dd> + <dt><b></b></dt> + <dd><li>Alice opens an anonymous stream to one of Bob's introduction + points, and gives it a message (encrypted with Bob's public key) + telling it about herself, + her RP and rendezvous cookie, and the + start of a DH + handshake. The introduction point sends the message to Bob.</dd> + <dt><b></b></dt> + <dd><li>If Bob wants to talk to Alice, he builds a circuit to Alice's + RP and sends the rendezvous cookie, the second half of the DH + handshake, and a hash of the session + key they now share. By the same argument as in + Section <a href="#subsubsec:constructing-a-circuit">4.2</a>, Alice knows she + shares the key only with Bob.</dd> + <dt><b></b></dt> + <dd><li>The RP connects Alice's circuit to Bob's. Note that RP can't + recognize Alice, Bob, or the data they transmit.</dd> + <dt><b></b></dt> + <dd><li>Alice sends a <em>relay begin</em> cell along the circuit. It + arrives at Bob's OP, which connects to Bob's + webserver.</dd> + <dt><b></b></dt> + <dd><li>An anonymous stream has been established, and Alice and Bob + communicate as normal. +</dd> +</dl> + +<div class="p"><!----></div> +When establishing an introduction point, Bob provides the onion router +with the public key identifying his service. Bob signs his +messages, so others cannot usurp his introduction point +in the future. He uses the same public key to establish the other +introduction points for his service, and periodically refreshes his +entry in the lookup service. + +<div class="p"><!----></div> +The message that Alice gives +the introduction point includes a hash of Bob's public key and an optional initial authorization token (the +introduction point can do prescreening, for example to block replays). Her +message to Bob may include an end-to-end authorization token so Bob +can choose whether to respond. +The authorization tokens can be used to provide selective access: +important users can get uninterrupted access. +During normal situations, Bob's service might simply be offered +directly from mirrors, while Bob gives out tokens to high-priority users. If +the mirrors are knocked down, +those users can switch to accessing Bob's service via +the Tor rendezvous system. + +<div class="p"><!----></div> +Bob's introduction points are themselves subject to DoS-he must +open many introduction points or risk such an attack. +He can provide selected users with a current list or future schedule of +unadvertised introduction points; +this is most practical +if there is a stable and large group of introduction points +available. Bob could also give secret public keys +for consulting the lookup service. All of these approaches +limit exposure even when +some selected users collude in the DoS. + +<div class="p"><!----></div> + <h3><a name="tth_sEc5.2"> +5.2</a> Integration with user applications</h3> + +<div class="p"><!----></div> +Bob configures his onion proxy to know the local IP address and port of his +service, a strategy for authorizing clients, and his public key. The onion +proxy anonymously publishes a signed statement of Bob's +public key, an expiration time, and +the current introduction points for his service onto the lookup service, +indexed +by the hash of his public key. Bob's webserver is unmodified, +and doesn't even know that it's hidden behind the Tor network. + +<div class="p"><!----></div> +Alice's applications also work unchanged-her client interface +remains a SOCKS proxy. We encode all of the necessary information +into the fully qualified domain name (FQDN) Alice uses when establishing her +connection. Location-hidden services use a virtual top level domain +called <tt>.onion</tt>: thus hostnames take the form <tt>x.y.onion</tt> where +<tt>x</tt> is the authorization cookie and <tt>y</tt> encodes the hash of +the public key. Alice's onion proxy +examines addresses; if they're destined for a hidden server, it decodes +the key and starts the rendezvous as described above. + +<div class="p"><!----></div> + <h3><a name="tth_sEc5.3"> +5.3</a> Previous rendezvous work</h3> + +<div class="p"><!----></div> +Rendezvous points in low-latency anonymity systems were first +described for use in ISDN telephony [<a href="#jerichow-jsac98" name="CITEjerichow-jsac98">30</a>,<a href="#isdn-mixes" name="CITEisdn-mixes">38</a>]. +Later low-latency designs used rendezvous points for hiding location +of mobile phones and low-power location +trackers [<a href="#federrath-ih96" name="CITEfederrath-ih96">23</a>,<a href="#reed-protocols97" name="CITEreed-protocols97">40</a>]. Rendezvous for +anonymizing low-latency +Internet connections was suggested in early Onion Routing +work [<a href="#or-ih96" name="CITEor-ih96">27</a>], but the first published design was by Ian +Goldberg [<a href="#ian-thesis" name="CITEian-thesis">26</a>]. His design differs from +ours in three ways. First, Goldberg suggests that Alice should manually +hunt down a current location of the service via Gnutella; our approach +makes lookup transparent to the user, as well as faster and more robust. +Second, in Tor the client and server negotiate session keys +with Diffie-Hellman, so plaintext is not exposed even at the rendezvous +point. Third, +our design minimizes the exposure from running the +service, to encourage volunteers to offer introduction and rendezvous +services. Tor's introduction points do not output any bytes to the +clients; the rendezvous points don't know the client or the server, +and can't read the data being transmitted. The indirection scheme is +also designed to include authentication/authorization-if Alice doesn't +include the right cookie with her request for service, Bob need not even +acknowledge his existence. + +<div class="p"><!----></div> + <h2><a name="tth_sEc6"> +6</a> Other design decisions</h2> +<a name="sec:other-design"> +</a> + +<div class="p"><!----></div> + <h3><a name="tth_sEc6.1"> +6.1</a> Denial of service</h3> +<a name="subsec:dos"> +</a> + +<div class="p"><!----></div> +Providing Tor as a public service creates many opportunities for +denial-of-service attacks against the network. While +flow control and rate limiting (discussed in +Section <a href="#subsec:congestion">4.6</a>) prevent users from consuming more +bandwidth than routers are willing to provide, opportunities remain for +users to +consume more network resources than their fair share, or to render the +network unusable for others. + +<div class="p"><!----></div> +First of all, there are several CPU-consuming denial-of-service +attacks wherein an attacker can force an OR to perform expensive +cryptographic operations. For example, an attacker can +fake the start of a TLS handshake, forcing the OR to carry out its +(comparatively expensive) half of the handshake at no real computational +cost to the attacker. + +<div class="p"><!----></div> +We have not yet implemented any defenses for these attacks, but several +approaches are possible. First, ORs can +require clients to solve a puzzle [<a href="#puzzles-tls" name="CITEpuzzles-tls">16</a>] while beginning new +TLS handshakes or accepting <em>create</em> cells. So long as these +tokens are easy to verify and computationally expensive to produce, this +approach limits the attack multiplier. Additionally, ORs can limit +the rate at which they accept <em>create</em> cells and TLS connections, +so that +the computational work of processing them does not drown out the +symmetric cryptography operations that keep cells +flowing. This rate limiting could, however, allow an attacker +to slow down other users when they build new circuits. + +<div class="p"><!----></div> + +<div class="p"><!----></div> +Adversaries can also attack the Tor network's hosts and network +links. Disrupting a single circuit or link breaks all streams passing +along that part of the circuit. Users similarly lose service +when a router crashes or its operator restarts it. The current +Tor design treats such attacks as intermittent network failures, and +depends on users and applications to respond or recover as appropriate. A +future design could use an end-to-end TCP-like acknowledgment protocol, +so no streams are lost unless the entry or exit point is +disrupted. This solution would require more buffering at the network +edges, however, and the performance and anonymity implications from this +extra complexity still require investigation. + +<div class="p"><!----></div> + <h3><a name="tth_sEc6.2"> +6.2</a> Exit policies and abuse</h3> +<a name="subsec:exitpolicies"> +</a> + +<div class="p"><!----></div> + +<div class="p"><!----></div> +Exit abuse is a serious barrier to wide-scale Tor deployment. Anonymity +presents would-be vandals and abusers with an opportunity to hide +the origins of their activities. Attackers can harm the Tor network by +implicating exit servers for their abuse. Also, applications that commonly +use IP-based authentication (such as institutional mail or webservers) +can be fooled by the fact that anonymous connections appear to originate +at the exit OR. + +<div class="p"><!----></div> +We stress that Tor does not enable any new class of abuse. Spammers +and other attackers already have access to thousands of misconfigured +systems worldwide, and the Tor network is far from the easiest way +to launch attacks. +But because the +onion routers can be mistaken for the originators of the abuse, +and the volunteers who run them may not want to deal with the hassle of +explaining anonymity networks to irate administrators, we must block or limit +abuse through the Tor network. + +<div class="p"><!----></div> +To mitigate abuse issues, each onion router's <em>exit policy</em> +describes to which external addresses and ports the router will +connect. On one end of the spectrum are <em>open exit</em> +nodes that will connect anywhere. On the other end are <em>middleman</em> +nodes that only relay traffic to other Tor nodes, and <em>private exit</em> +nodes that only connect to a local host or network. A private +exit can allow a client to connect to a given host or +network more securely-an external adversary cannot eavesdrop traffic +between the private exit and the final destination, and so is less sure of +Alice's destination and activities. Most onion routers in the current +network function as +<em>restricted exits</em> that permit connections to the world at large, +but prevent access to certain abuse-prone addresses and services such +as SMTP. +The OR might also be able to authenticate clients to +prevent exit abuse without harming anonymity [<a href="#or-discex00" name="CITEor-discex00">48</a>]. + +<div class="p"><!----></div> + +<div class="p"><!----></div> +Many administrators use port restrictions to support only a +limited set of services, such as HTTP, SSH, or AIM. +This is not a complete solution, of course, since abuse opportunities for these +protocols are still well known. + +<div class="p"><!----></div> +We have not yet encountered any abuse in the deployed network, but if +we do we should consider using proxies to clean traffic for certain +protocols as it leaves the network. For example, much abusive HTTP +behavior (such as exploiting buffer overflows or well-known script +vulnerabilities) can be detected in a straightforward manner. +Similarly, one could run automatic spam filtering software (such as +SpamAssassin) on email exiting the OR network. + +<div class="p"><!----></div> +ORs may also rewrite exiting traffic to append +headers or other information indicating that the traffic has passed +through an anonymity service. This approach is commonly used +by email-only anonymity systems. ORs can also +run on servers with hostnames like <tt>anonymous</tt> to further +alert abuse targets to the nature of the anonymous traffic. + +<div class="p"><!----></div> +A mixture of open and restricted exit nodes allows the most +flexibility for volunteers running servers. But while having many +middleman nodes provides a large and robust network, +having only a few exit nodes reduces the number of points +an adversary needs to monitor for traffic analysis, and places a +greater burden on the exit nodes. This tension can be seen in the +Java Anon Proxy +cascade model, wherein only one node in each cascade needs to handle +abuse complaints-but an adversary only needs to observe the entry +and exit of a cascade to perform traffic analysis on all that +cascade's users. The hydra model (many entries, few exits) presents a +different compromise: only a few exit nodes are needed, but an +adversary needs to work harder to watch all the clients; see +Section <a href="#sec:conclusion">10</a>. + +<div class="p"><!----></div> +Finally, we note that exit abuse must not be dismissed as a peripheral +issue: when a system's public image suffers, it can reduce the number +and diversity of that system's users, and thereby reduce the anonymity +of the system itself. Like usability, public perception is a +security parameter. Sadly, preventing abuse of open exit nodes is an +unsolved problem, and will probably remain an arms race for the +foreseeable future. The abuse problems faced by Princeton's CoDeeN +project [<a href="#darkside" name="CITEdarkside">37</a>] give us a glimpse of likely issues. + +<div class="p"><!----></div> + <h3><a name="tth_sEc6.3"> +6.3</a> Directory Servers</h3> +<a name="subsec:dirservers"> +</a> + +<div class="p"><!----></div> +First-generation Onion Routing designs [<a href="#freedom2-arch" name="CITEfreedom2-arch">8</a>,<a href="#or-jsac98" name="CITEor-jsac98">41</a>] used +in-band network status updates: each router flooded a signed statement +to its neighbors, which propagated it onward. But anonymizing networks +have different security goals than typical link-state routing protocols. +For example, delays (accidental or intentional) +that can cause different parts of the network to have different views +of link-state and topology are not only inconvenient: they give +attackers an opportunity to exploit differences in client knowledge. +We also worry about attacks to deceive a +client about the router membership list, topology, or current network +state. Such <em>partitioning attacks</em> on client knowledge help an +adversary to efficiently deploy resources +against a target [<a href="#minion-design" name="CITEminion-design">15</a>]. + +<div class="p"><!----></div> +Tor uses a small group of redundant, well-known onion routers to +track changes in network topology and node state, including keys and +exit policies. Each such <em>directory server</em> acts as an HTTP +server, so clients can fetch current network state +and router lists, and so other ORs can upload +state information. Onion routers periodically publish signed +statements of their state to each directory server. The directory servers +combine this information with their own views of network liveness, +and generate a signed description (a <em>directory</em>) of the entire +network state. Client software is +pre-loaded with a list of the directory servers and their keys, +to bootstrap each client's view of the network. + +<div class="p"><!----></div> +When a directory server receives a signed statement for an OR, it +checks whether the OR's identity key is recognized. Directory +servers do not advertise unrecognized ORs-if they did, +an adversary could take over the network by creating many +servers [<a href="#sybil" name="CITEsybil">22</a>]. Instead, new nodes must be approved by the +directory +server administrator before they are included. Mechanisms for automated +node approval are an area of active research, and are discussed more +in Section <a href="#sec:maintaining-anonymity">9</a>. + +<div class="p"><!----></div> +Of course, a variety of attacks remain. An adversary who controls +a directory server can track clients by providing them different +information-perhaps by listing only nodes under its control, or by +informing only certain clients about a given node. Even an external +adversary can exploit differences in client knowledge: clients who use +a node listed on one directory server but not the others are vulnerable. + +<div class="p"><!----></div> +Thus these directory servers must be synchronized and redundant, so +that they can agree on a common directory. Clients should only trust +this directory if it is signed by a threshold of the directory +servers. + +<div class="p"><!----></div> +The directory servers in Tor are modeled after those in +Mixminion [<a href="#minion-design" name="CITEminion-design">15</a>], but our situation is easier. First, +we make the +simplifying assumption that all participants agree on the set of +directory servers. Second, while Mixminion needs to predict node +behavior, Tor only needs a threshold consensus of the current +state of the network. Third, we assume that we can fall back to the +human administrators to discover and resolve problems when a consensus +directory cannot be reached. Since there are relatively few directory +servers (currently 3, but we expect as many as 9 as the network scales), +we can afford operations like broadcast to simplify the consensus-building +protocol. + +<div class="p"><!----></div> +To avoid attacks where a router connects to all the directory servers +but refuses to relay traffic from other routers, the directory servers +must also build circuits and use them to anonymously test router +reliability [<a href="#mix-acc" name="CITEmix-acc">18</a>]. Unfortunately, this defense is not yet +designed or +implemented. + +<div class="p"><!----></div> +Using directory servers is simpler and more flexible than flooding. +Flooding is expensive, and complicates the analysis when we +start experimenting with non-clique network topologies. Signed +directories can be cached by other +onion routers, +so directory servers are not a performance +bottleneck when we have many users, and do not aid traffic analysis by +forcing clients to announce their existence to any +central point. + +<div class="p"><!----></div> + <h2><a name="tth_sEc7"> +7</a> Attacks and Defenses</h2> +<a name="sec:attacks"> +</a> + +<div class="p"><!----></div> +Below we summarize a variety of attacks, and discuss how well our +design withstands them.<br /> + +<div class="p"><!----></div> +<font size="+1"><b>Passive attacks</b></font><br /> +<em>Observing user traffic patterns.</em> Observing a user's connection +will not reveal her destination or data, but it will +reveal traffic patterns (both sent and received). Profiling via user +connection patterns requires further processing, because multiple +application streams may be operating simultaneously or in series over +a single circuit. + +<div class="p"><!----></div> +<em>Observing user content.</em> While content at the user end is encrypted, +connections to responders may not be (indeed, the responding website +itself may be hostile). While filtering content is not a primary goal +of Onion Routing, Tor can directly use Privoxy and related +filtering services to anonymize application data streams. + +<div class="p"><!----></div> +<em>Option distinguishability.</em> We allow clients to choose +configuration options. For example, clients concerned about request +linkability should rotate circuits more often than those concerned +about traceability. Allowing choice may attract users with different +needs; but clients who are +in the minority may lose more anonymity by appearing distinct than they +gain by optimizing their behavior [<a href="#econymics" name="CITEeconymics">1</a>]. + +<div class="p"><!----></div> +<em>End-to-end timing correlation.</em> Tor only minimally hides +such correlations. An attacker watching patterns of +traffic at the initiator and the responder will be +able to confirm the correspondence with high probability. The +greatest protection currently available against such confirmation is to hide +the connection between the onion proxy and the first Tor node, +by running the OP on the Tor node or behind a firewall. This approach +requires an observer to separate traffic originating at the onion +router from traffic passing through it: a global observer can do this, +but it might be beyond a limited observer's capabilities. + +<div class="p"><!----></div> +<em>End-to-end size correlation.</em> Simple packet counting +will also be effective in confirming +endpoints of a stream. However, even without padding, we may have some +limited protection: the leaky pipe topology means different numbers +of packets may enter one end of a circuit than exit at the other. + +<div class="p"><!----></div> +<em>Website fingerprinting.</em> All the effective passive +attacks above are traffic confirmation attacks, +which puts them outside our design goals. There is also +a passive traffic analysis attack that is potentially effective. +Rather than searching exit connections for timing and volume +correlations, the adversary may build up a database of +"fingerprints" containing file sizes and access patterns for +targeted websites. He can later confirm a user's connection to a given +site simply by consulting the database. This attack has +been shown to be effective against SafeWeb [<a href="#hintz-pet02" name="CITEhintz-pet02">29</a>]. +It may be less effective against Tor, since +streams are multiplexed within the same circuit, and +fingerprinting will be limited to +the granularity of cells (currently 512 bytes). Additional +defenses could include +larger cell sizes, padding schemes to group websites +into large sets, and link +padding or long-range dummies.<a href="#tthFtNtAAE" name="tthFrefAAE"><sup>4</sup></a><br /> + +<div class="p"><!----></div> +<font size="+1"><b>Active attacks</b></font><br /> +<em>Compromise keys.</em> An attacker who learns the TLS session key can +see control cells and encrypted relay cells on every circuit on that +connection; learning a circuit +session key lets him unwrap one layer of the encryption. An attacker +who learns an OR's TLS private key can impersonate that OR for the TLS +key's lifetime, but he must +also learn the onion key to decrypt <em>create</em> cells (and because of +perfect forward secrecy, he cannot hijack already established circuits +without also compromising their session keys). Periodic key rotation +limits the window of opportunity for these attacks. On the other hand, +an attacker who learns a node's identity key can replace that node +indefinitely by sending new forged descriptors to the directory servers. + +<div class="p"><!----></div> +<em>Iterated compromise.</em> A roving adversary who can +compromise ORs (by system intrusion, legal coercion, or extralegal +coercion) could march down the circuit compromising the +nodes until he reaches the end. Unless the adversary can complete +this attack within the lifetime of the circuit, however, the ORs +will have discarded the necessary information before the attack can +be completed. (Thanks to the perfect forward secrecy of session +keys, the attacker cannot force nodes to decrypt recorded +traffic once the circuits have been closed.) Additionally, building +circuits that cross jurisdictions can make legal coercion +harder-this phenomenon is commonly called "jurisdictional +arbitrage." The Java Anon Proxy project recently experienced the +need for this approach, when +a German court forced them to add a backdoor to +their nodes [<a href="#jap-backdoor" name="CITEjap-backdoor">51</a>]. + +<div class="p"><!----></div> +<em>Run a recipient.</em> An adversary running a webserver +trivially learns the timing patterns of users connecting to it, and +can introduce arbitrary patterns in its responses. +End-to-end attacks become easier: if the adversary can induce +users to connect to his webserver (perhaps by advertising +content targeted to those users), he now holds one end of their +connection. There is also a danger that application +protocols and associated programs can be induced to reveal information +about the initiator. Tor depends on Privoxy and similar protocol cleaners +to solve this latter problem. + +<div class="p"><!----></div> +<em>Run an onion proxy.</em> It is expected that end users will +nearly always run their own local onion proxy. However, in some +settings, it may be necessary for the proxy to run +remotely-typically, in institutions that want +to monitor the activity of those connecting to the proxy. +Compromising an onion proxy compromises all future connections +through it. + +<div class="p"><!----></div> +<em>DoS non-observed nodes.</em> An observer who can only watch some +of the Tor network can increase the value of this traffic +by attacking non-observed nodes to shut them down, reduce +their reliability, or persuade users that they are not trustworthy. +The best defense here is robustness. + +<div class="p"><!----></div> +<em>Run a hostile OR.</em> In addition to being a local observer, +an isolated hostile node can create circuits through itself, or alter +traffic patterns to affect traffic at other nodes. Nonetheless, a hostile +node must be immediately adjacent to both endpoints to compromise the +anonymity of a circuit. If an adversary can +run multiple ORs, and can persuade the directory servers +that those ORs are trustworthy and independent, then occasionally +some user will choose one of those ORs for the start and another +as the end of a circuit. If an adversary +controls m > 1 of N nodes, he can correlate at most +([m/N])<sup>2</sup> of the traffic-although an +adversary +could still attract a disproportionately large amount of traffic +by running an OR with a permissive exit policy, or by +degrading the reliability of other routers. + +<div class="p"><!----></div> +<em>Introduce timing into messages.</em> This is simply a stronger +version of passive timing attacks already discussed earlier. + +<div class="p"><!----></div> +<em>Tagging attacks.</em> A hostile node could "tag" a +cell by altering it. If the +stream were, for example, an unencrypted request to a Web site, +the garbled content coming out at the appropriate time would confirm +the association. However, integrity checks on cells prevent +this attack. + +<div class="p"><!----></div> +<em>Replace contents of unauthenticated protocols.</em> When +relaying an unauthenticated protocol like HTTP, a hostile exit node +can impersonate the target server. Clients +should prefer protocols with end-to-end authentication. + +<div class="p"><!----></div> +<em>Replay attacks.</em> Some anonymity protocols are vulnerable +to replay attacks. Tor is not; replaying one side of a handshake +will result in a different negotiated session key, and so the rest +of the recorded session can't be used. + +<div class="p"><!----></div> +<em>Smear attacks.</em> An attacker could use the Tor network for +socially disapproved acts, to bring the +network into disrepute and get its operators to shut it down. +Exit policies reduce the possibilities for abuse, but +ultimately the network requires volunteers who can tolerate +some political heat. + +<div class="p"><!----></div> +<em>Distribute hostile code.</em> An attacker could trick users +into running subverted Tor software that did not, in fact, anonymize +their connections-or worse, could trick ORs into running weakened +software that provided users with less anonymity. We address this +problem (but do not solve it completely) by signing all Tor releases +with an official public key, and including an entry in the directory +that lists which versions are currently believed to be secure. To +prevent an attacker from subverting the official release itself +(through threats, bribery, or insider attacks), we provide all +releases in source code form, encourage source audits, and +frequently warn our users never to trust any software (even from +us) that comes without source.<br /> + +<div class="p"><!----></div> +<font size="+1"><b>Directory attacks</b></font><br /> +<em>Destroy directory servers.</em> If a few directory +servers disappear, the others still decide on a valid +directory. So long as any directory servers remain in operation, +they will still broadcast their views of the network and generate a +consensus directory. (If more than half are destroyed, this +directory will not, however, have enough signatures for clients to +use it automatically; human intervention will be necessary for +clients to decide whether to trust the resulting directory.) + +<div class="p"><!----></div> +<em>Subvert a directory server.</em> By taking over a directory server, +an attacker can partially influence the final directory. Since ORs +are included or excluded by majority vote, the corrupt directory can +at worst cast a tie-breaking vote to decide whether to include +marginal ORs. It remains to be seen how often such marginal cases +occur in practice. + +<div class="p"><!----></div> +<em>Subvert a majority of directory servers.</em> An adversary who controls +more than half the directory servers can include as many compromised +ORs in the final directory as he wishes. We must ensure that directory +server operators are independent and attack-resistant. + +<div class="p"><!----></div> +<em>Encourage directory server dissent.</em> The directory +agreement protocol assumes that directory server operators agree on +the set of directory servers. An adversary who can persuade some +of the directory server operators to distrust one another could +split the quorum into mutually hostile camps, thus partitioning +users based on which directory they use. Tor does not address +this attack. + +<div class="p"><!----></div> +<em>Trick the directory servers into listing a hostile OR.</em> +Our threat model explicitly assumes directory server operators will +be able to filter out most hostile ORs. + +<div class="p"><!----></div> +<em>Convince the directories that a malfunctioning OR is +working.</em> In the current Tor implementation, directory servers +assume that an OR is running correctly if they can start a TLS +connection to it. A hostile OR could easily subvert this test by +accepting TLS connections from ORs but ignoring all cells. Directory +servers must actively test ORs by building circuits and streams as +appropriate. The tradeoffs of a similar approach are discussed +in [<a href="#mix-acc" name="CITEmix-acc">18</a>].<br /> + +<div class="p"><!----></div> +<font size="+1"><b>Attacks against rendezvous points</b></font><br /> +<em>Make many introduction requests.</em> An attacker could +try to deny Bob service by flooding his introduction points with +requests. Because the introduction points can block requests that +lack authorization tokens, however, Bob can restrict the volume of +requests he receives, or require a certain amount of computation for +every request he receives. + +<div class="p"><!----></div> +<em>Attack an introduction point.</em> An attacker could +disrupt a location-hidden service by disabling its introduction +points. But because a service's identity is attached to its public +key, the service can simply re-advertise +itself at a different introduction point. Advertisements can also be +done secretly so that only high-priority clients know the address of +Bob's introduction points or so that different clients know of different +introduction points. This forces the attacker to disable all possible +introduction points. + +<div class="p"><!----></div> +<em>Compromise an introduction point.</em> An attacker who controls +Bob's introduction point can flood Bob with +introduction requests, or prevent valid introduction requests from +reaching him. Bob can notice a flood, and close the circuit. To notice +blocking of valid requests, however, he should periodically test the +introduction point by sending rendezvous requests and making +sure he receives them. + +<div class="p"><!----></div> +<em>Compromise a rendezvous point.</em> A rendezvous +point is no more sensitive than any other OR on +a circuit, since all data passing through the rendezvous is encrypted +with a session key shared by Alice and Bob. + +<div class="p"><!----></div> + <h2><a name="tth_sEc8"> +8</a> Early experiences: Tor in the Wild</h2> +<a name="sec:in-the-wild"> +</a> + +<div class="p"><!----></div> +As of mid-May 2004, the Tor network consists of 32 nodes +(24 in the US, 8 in Europe), and more are joining each week as the code +matures. (For comparison, the current remailer network +has about 40 nodes.) Each node has at least a 768Kb/768Kb connection, and +many have 10Mb. The number of users varies (and of course, it's hard to +tell for sure), but we sometimes have several hundred users-administrators at +several companies have begun sending their entire departments' web +traffic through Tor, to block other divisions of +their company from reading their traffic. Tor users have reported using +the network for web browsing, FTP, IRC, AIM, Kazaa, SSH, and +recipient-anonymous email via rendezvous points. One user has anonymously +set up a Wiki as a hidden service, where other users anonymously publish +the addresses of their hidden services. + +<div class="p"><!----></div> +Each Tor node currently processes roughly 800,000 relay +cells (a bit under half a gigabyte) per week. On average, about 80% +of each 498-byte payload is full for cells going back to the client, +whereas about 40% is full for cells coming from the client. (The difference +arises because most of the network's traffic is web browsing.) Interactive +traffic like SSH brings down the average a lot-once we have more +experience, and assuming we can resolve the anonymity issues, we may +partition traffic into two relay cell sizes: one to handle +bulk traffic and one for interactive traffic. + +<div class="p"><!----></div> +Based in part on our restrictive default exit policy (we +reject SMTP requests) and our low profile, we have had no abuse +issues since the network was deployed in October +2003. Our slow growth rate gives us time to add features, +resolve bugs, and get a feel for what users actually want from an +anonymity system. Even though having more users would bolster our +anonymity sets, we are not eager to attract the Kazaa or warez +communities-we feel that we must build a reputation for privacy, human +rights, research, and other socially laudable activities. + +<div class="p"><!----></div> +As for performance, profiling shows that Tor spends almost +all its CPU time in AES, which is fast. Current latency is attributable +to two factors. First, network latency is critical: we are +intentionally bouncing traffic around the world several times. Second, +our end-to-end congestion control algorithm focuses on protecting +volunteer servers from accidental DoS rather than on optimizing +performance. To quantify these effects, we did some informal tests using a network of 4 +nodes on the same machine (a heavily loaded 1GHz Athlon). We downloaded a 60 +megabyte file from <tt>debian.org</tt> every 30 minutes for 54 hours (108 sample +points). It arrived in about 300 seconds on average, compared to 210s for a +direct download. We ran a similar test on the production Tor network, +fetching the front page of <tt>cnn.com</tt> (55 kilobytes): +while a direct +download consistently took about 0.3s, the performance through Tor varied. +Some downloads were as fast as 0.4s, with a median at 2.8s, and +90% finishing within 5.3s. It seems that as the network expands, the chance +of building a slow circuit (one that includes a slow or heavily loaded node +or link) is increasing. On the other hand, as our users remain satisfied +with this increased latency, we can address our performance incrementally as we +proceed with development. +<div class="p"><!----></div> + +<div class="p"><!----></div> + +<div class="p"><!----></div> +Although Tor's clique topology and full-visibility directories present +scaling problems, we still expect the network to support a few hundred +nodes and maybe 10,000 users before we're forced to become +more distributed. With luck, the experience we gain running the current +topology will help us choose among alternatives when the time comes. + +<div class="p"><!----></div> + <h2><a name="tth_sEc9"> +9</a> Open Questions in Low-latency Anonymity</h2> +<a name="sec:maintaining-anonymity"> +</a> + +<div class="p"><!----></div> +In addition to the non-goals in +Section <a href="#subsec:non-goals">3</a>, many questions must be solved +before we can be confident of Tor's security. + +<div class="p"><!----></div> +Many of these open issues are questions of balance. For example, +how often should users rotate to fresh circuits? Frequent rotation +is inefficient, expensive, and may lead to intersection attacks and +predecessor attacks [<a href="#wright03" name="CITEwright03">54</a>], but infrequent rotation makes the +user's traffic linkable. Besides opening fresh circuits, clients can +also exit from the middle of the circuit, +or truncate and re-extend the circuit. More analysis is +needed to determine the proper tradeoff. + +<div class="p"><!----></div> + +<div class="p"><!----></div> +How should we choose path lengths? If Alice always uses two hops, +then both ORs can be certain that by colluding they will learn about +Alice and Bob. In our current approach, Alice always chooses at least +three nodes unrelated to herself and her destination. +Should Alice choose a random path length (e.g. from a geometric +distribution) to foil an attacker who +uses timing to learn that he is the fifth hop and thus concludes that +both Alice and the responder are running ORs? + +<div class="p"><!----></div> +Throughout this paper, we have assumed that end-to-end traffic +confirmation will immediately and automatically defeat a low-latency +anonymity system. Even high-latency anonymity systems can be +vulnerable to end-to-end traffic confirmation, if the traffic volumes +are high enough, and if users' habits are sufficiently +distinct [<a href="#statistical-disclosure" name="CITEstatistical-disclosure">14</a>,<a href="#limits-open" name="CITElimits-open">31</a>]. Can anything be +done to +make low-latency systems resist these attacks as well as high-latency +systems? Tor already makes some effort to conceal the starts and ends of +streams by wrapping long-range control commands in identical-looking +relay cells. Link padding could frustrate passive observers who count +packets; long-range padding could work against observers who own the +first hop in a circuit. But more research remains to find an efficient +and practical approach. Volunteers prefer not to run constant-bandwidth +padding; but no convincing traffic shaping approach has been +specified. Recent work on long-range padding [<a href="#defensive-dropping" name="CITEdefensive-dropping">33</a>] +shows promise. One could also try to reduce correlation in packet timing +by batching and re-ordering packets, but it is unclear whether this could +improve anonymity without introducing so much latency as to render the +network unusable. + +<div class="p"><!----></div> +A cascade topology may better defend against traffic confirmation by +aggregating users, and making padding and +mixing more affordable. Does the hydra topology (many input nodes, +few output nodes) work better against some adversaries? Are we going +to get a hydra anyway because most nodes will be middleman nodes? + +<div class="p"><!----></div> +Common wisdom suggests that Alice should run her own OR for best +anonymity, because traffic coming from her node could plausibly have +come from elsewhere. How much mixing does this approach need? Is it +immediately beneficial because of real-world adversaries that can't +observe Alice's router, but can run routers of their own? + +<div class="p"><!----></div> +To scale to many users, and to prevent an attacker from observing the +whole network, it may be necessary +to support far more servers than Tor currently anticipates. +This introduces several issues. First, if approval by a central set +of directory servers is no longer feasible, what mechanism should be used +to prevent adversaries from signing up many colluding servers? Second, +if clients can no longer have a complete picture of the network, +how can they perform discovery while preventing attackers from +manipulating or exploiting gaps in their knowledge? Third, if there +are too many servers for every server to constantly communicate with +every other, which non-clique topology should the network use? +(Restricted-route topologies promise comparable anonymity with better +scalability [<a href="#danezis-pets03" name="CITEdanezis-pets03">13</a>], but whatever topology we choose, we +need some way to keep attackers from manipulating their position within +it [<a href="#casc-rep" name="CITEcasc-rep">21</a>].) Fourth, if no central authority is tracking +server reliability, how do we stop unreliable servers from making +the network unusable? Fifth, do clients receive so much anonymity +from running their own ORs that we should expect them all to do +so [<a href="#econymics" name="CITEeconymics">1</a>], or do we need another incentive structure to +motivate them? Tarzan and MorphMix present possible solutions. + +<div class="p"><!----></div> + +<div class="p"><!----></div> +When a Tor node goes down, all its circuits (and thus streams) must break. +Will users abandon the system because of this brittleness? How well +does the method in Section <a href="#subsec:dos">6.1</a> allow streams to survive +node failure? If affected users rebuild circuits immediately, how much +anonymity is lost? It seems the problem is even worse in a peer-to-peer +environment-such systems don't yet provide an incentive for peers to +stay connected when they're done retrieving content, so we would expect +a higher churn rate. + +<div class="p"><!----></div> + +<div class="p"><!----></div> + <h2><a name="tth_sEc10"> +10</a> Future Directions</h2> +<a name="sec:conclusion"> +</a> + +<div class="p"><!----></div> +Tor brings together many innovations into a unified deployable system. The +next immediate steps include: + +<div class="p"><!----></div> +<em>Scalability:</em> Tor's emphasis on deployability and design simplicity +has led us to adopt a clique topology, semi-centralized +directories, and a full-network-visibility model for client +knowledge. These properties will not scale past a few hundred servers. +Section <a href="#sec:maintaining-anonymity">9</a> describes some promising +approaches, but more deployment experience will be helpful in learning +the relative importance of these bottlenecks. + +<div class="p"><!----></div> +<em>Bandwidth classes:</em> This paper assumes that all ORs have +good bandwidth and latency. We should instead adopt the MorphMix model, +where nodes advertise their bandwidth level (DSL, T1, T3), and +Alice avoids bottlenecks by choosing nodes that match or +exceed her bandwidth. In this way DSL users can usefully join the Tor +network. + +<div class="p"><!----></div> +<em>Incentives:</em> Volunteers who run nodes are rewarded with publicity +and possibly better anonymity [<a href="#econymics" name="CITEeconymics">1</a>]. More nodes means increased +scalability, and more users can mean more anonymity. We need to continue +examining the incentive structures for participating in Tor. Further, +we need to explore more approaches to limiting abuse, and understand +why most people don't bother using privacy systems. + +<div class="p"><!----></div> +<em>Cover traffic:</em> Currently Tor omits cover traffic-its costs +in performance and bandwidth are clear but its security benefits are +not well understood. We must pursue more research on link-level cover +traffic and long-range cover traffic to determine whether some simple padding +method offers provable protection against our chosen adversary. + +<div class="p"><!----></div> + +<div class="p"><!----></div> +<em>Caching at exit nodes:</em> Perhaps each exit node should run a +caching web proxy [<a href="#shsm03" name="CITEshsm03">47</a>], to improve anonymity for cached pages +(Alice's request never +leaves the Tor network), to improve speed, and to reduce bandwidth cost. +On the other hand, forward security is weakened because caches +constitute a record of retrieved files. We must find the right +balance between usability and security. + +<div class="p"><!----></div> +<em>Better directory distribution:</em> +Clients currently download a description of +the entire network every 15 minutes. As the state grows larger +and clients more numerous, we may need a solution in which +clients receive incremental updates to directory state. +More generally, we must find more +scalable yet practical ways to distribute up-to-date snapshots of +network status without introducing new attacks. + +<div class="p"><!----></div> +<em>Further specification review:</em> Our public +byte-level specification [<a href="#tor-spec" name="CITEtor-spec">20</a>] needs +external review. We hope that as Tor +is deployed, more people will examine its +specification. + +<div class="p"><!----></div> +<em>Multisystem interoperability:</em> We are currently working with the +designer of MorphMix to unify the specification and implementation of +the common elements of our two systems. So far, this seems +to be relatively straightforward. Interoperability will allow testing +and direct comparison of the two designs for trust and scalability. + +<div class="p"><!----></div> +<em>Wider-scale deployment:</em> The original goal of Tor was to +gain experience in deploying an anonymizing overlay network, and +learn from having actual users. We are now at a point in design +and development where we can start deploying a wider network. Once +we have many actual users, we will doubtlessly be better +able to evaluate some of our design decisions, including our +robustness/latency tradeoffs, our performance tradeoffs (including +cell size), our abuse-prevention mechanisms, and +our overall usability. + +<div class="p"><!----></div> + +<div class="p"><!----></div> + +<h2>Acknowledgments</h2> + We thank Peter Palfrader, Geoff Goodell, Adam Shostack, Joseph Sokol-Margolis, + John Bashinski, and Zack Brown + for editing and comments; + Matej Pfajfar, Andrei Serjantov, Marc Rennhard for design discussions; + Bram Cohen for congestion control discussions; + Adam Back for suggesting telescoping circuits; and + Cathy Meadows for formal analysis of the <em>extend</em> protocol. + This work has been supported by ONR and DARPA. + +<div class="p"><!----></div> + +<div class="p"><!----></div> + +<div class="p"><!----></div> +<h2>References</h2> + +<dl compact="compact"> +<font size="-1"></font> <dt><a href="#CITEeconymics" name="econymics">[1]</a></dt><dd> +A. Acquisti, R. Dingledine, and P. Syverson. + On the economics of anonymity. + In R. N. Wright, editor, <em>Financial Cryptography</em>. + Springer-Verlag, LNCS 2742, 2003. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEeternity" name="eternity">[2]</a></dt><dd> +R. Anderson. + The eternity service. + In <em>Pragocrypt '96</em>, 1996. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEanonymizer" name="anonymizer">[3]</a></dt><dd> +The Anonymizer. + <tt><http://anonymizer.com/>. + +<div class="p"><!----></div> +</tt></dd> + <dt><a href="#CITEfreedom21-security" name="freedom21-security">[4]</a></dt><dd> +A. Back, I. Goldberg, and A. Shostack. + Freedom systems 2.1 security issues and analysis. + White paper, Zero Knowledge Systems, Inc., May 2001. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEback01" name="back01">[5]</a></dt><dd> +A. Back, U. Möller, and A. Stiglic. + Traffic analysis attacks and trade-offs in anonymity providing + systems. + In I. S. Moskowitz, editor, <em>Information Hiding (IH 2001)</em>, pages + 245-257. Springer-Verlag, LNCS 2137, 2001. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEeax" name="eax">[6]</a></dt><dd> +M. Bellare, P. Rogaway, and D. Wagner. + The EAX mode of operation: A two-pass authenticated-encryption + scheme optimized for simplicity and efficiency. + In <em>Fast Software Encryption 2004</em>, February 2004. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEweb-mix" name="web-mix">[7]</a></dt><dd> +O. Berthold, H. Federrath, and S. Köpsell. + Web MIXes: A system for anonymous and unobservable Internet + access. + In H. Federrath, editor, <em>Designing Privacy Enhancing + Technologies: Workshop on Design Issue in Anonymity and Unobservability</em>. + Springer-Verlag, LNCS 2009, 2000. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEfreedom2-arch" name="freedom2-arch">[8]</a></dt><dd> +P. Boucher, A. Shostack, and I. Goldberg. + Freedom systems 2.0 architecture. + White paper, Zero Knowledge Systems, Inc., December 2000. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEcebolla" name="cebolla">[9]</a></dt><dd> +Z. Brown. + Cebolla: Pragmatic IP Anonymity. + In <em>Ottawa Linux Symposium</em>, June 2002. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEchaum-mix" name="chaum-mix">[10]</a></dt><dd> +D. Chaum. + Untraceable electronic mail, return addresses, and digital + pseudo-nyms. + <em>Communications of the ACM</em>, 4(2), February 1981. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEcfs:sosp01" name="cfs:sosp01">[11]</a></dt><dd> +F. Dabek, M. F. Kaashoek, D. Karger, R. Morris, and I. Stoica. + Wide-area cooperative storage with CFS. + In <em>18th ACM Symposium on Operating Systems Principles + (SOSP '01)</em>, Chateau Lake Louise, Banff, Canada, October 2001. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEpipenet" name="pipenet">[12]</a></dt><dd> +W. Dai. + Pipenet 1.1. + Usenet post, August 1996. + <tt><http://www.eskimo.com/ weidai/pipenet.txt> First mentioned in a + post to the cypherpunks list, Feb. 1995. + +<div class="p"><!----></div> +</tt></dd> + <dt><a href="#CITEdanezis-pets03" name="danezis-pets03">[13]</a></dt><dd> +G. Danezis. + Mix-networks with restricted routes. + In R. Dingledine, editor, <em>Privacy Enhancing Technologies (PET + 2003)</em>. Springer-Verlag LNCS 2760, 2003. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEstatistical-disclosure" name="statistical-disclosure">[14]</a></dt><dd> +G. Danezis. + Statistical disclosure attacks. + In <em>Security and Privacy in the Age of Uncertainty (SEC2003)</em>, + pages 421-426, Athens, May 2003. IFIP TC11, Kluwer. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEminion-design" name="minion-design">[15]</a></dt><dd> +G. Danezis, R. Dingledine, and N. Mathewson. + Mixminion: Design of a type III anonymous remailer protocol. + In <em>2003 IEEE Symposium on Security and Privacy</em>, pages 2-15. + IEEE CS, May 2003. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEpuzzles-tls" name="puzzles-tls">[16]</a></dt><dd> +D. Dean and A. Stubblefield. + Using Client Puzzles to Protect TLS. + In <em>Proceedings of the 10th USENIX Security Symposium</em>. USENIX, + Aug. 2001. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITETLS" name="TLS">[17]</a></dt><dd> +T. Dierks and C. Allen. + The TLS Protocol - Version 1.0. + IETF RFC 2246, January 1999. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEmix-acc" name="mix-acc">[18]</a></dt><dd> +R. Dingledine, M. J. Freedman, D. Hopwood, and D. Molnar. + A Reputation System to Increase MIX-net Reliability. + In I. S. Moskowitz, editor, <em>Information Hiding (IH 2001)</em>, pages + 126-141. Springer-Verlag, LNCS 2137, 2001. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEfreehaven-berk" name="freehaven-berk">[19]</a></dt><dd> +R. Dingledine, M. J. Freedman, and D. Molnar. + The free haven project: Distributed anonymous storage service. + In H. Federrath, editor, <em>Designing Privacy Enhancing + Technologies: Workshop on Design Issue in Anonymity and Unobservability</em>. + Springer-Verlag, LNCS 2009, July 2000. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEtor-spec" name="tor-spec">[20]</a></dt><dd> +R. Dingledine and N. Mathewson. + Tor protocol specifications. + <tt><http://freehaven.net/tor/tor-spec.txt>. + +<div class="p"><!----></div> +</tt></dd> + <dt><a href="#CITEcasc-rep" name="casc-rep">[21]</a></dt><dd> +R. Dingledine and P. Syverson. + Reliable MIX Cascade Networks through Reputation. + In M. Blaze, editor, <em>Financial Cryptography</em>. Springer-Verlag, + LNCS 2357, 2002. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEsybil" name="sybil">[22]</a></dt><dd> +J. Douceur. + The Sybil Attack. + In <em>Proceedings of the 1st International Peer To Peer Systems + Workshop (IPTPS)</em>, Mar. 2002. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEfederrath-ih96" name="federrath-ih96">[23]</a></dt><dd> +H. Federrath, A. Jerichow, and A. Pfitzmann. + MIXes in mobile communication systems: Location management with + privacy. + In R. Anderson, editor, <em>Information Hiding, First International + Workshop</em>, pages 121-135. Springer-Verlag, LNCS 1174, May 1996. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEtarzan:ccs02" name="tarzan:ccs02">[24]</a></dt><dd> +M. J. Freedman and R. Morris. + Tarzan: A peer-to-peer anonymizing network layer. + In <em>9th ACM Conference on Computer and Communications + Security (CCS 2002)</em>, Washington, DC, November 2002. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEherbivore" name="herbivore">[25]</a></dt><dd> +S. Goel, M. Robson, M. Polte, and E. G. Sirer. + Herbivore: A scalable and efficient protocol for anonymous + communication. + Technical Report TR2003-1890, Cornell University Computing and + Information Science, February 2003. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEian-thesis" name="ian-thesis">[26]</a></dt><dd> +I. Goldberg. + <em>A Pseudonymous Communications Infrastructure for the Internet</em>. + PhD thesis, UC Berkeley, Dec 2000. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEor-ih96" name="or-ih96">[27]</a></dt><dd> +D. M. Goldschlag, M. G. Reed, and P. F. Syverson. + Hiding routing information. + In R. Anderson, editor, <em>Information Hiding, First International + Workshop</em>, pages 137-150. Springer-Verlag, LNCS 1174, May 1996. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEbabel" name="babel">[28]</a></dt><dd> +C. Gülcü and G. Tsudik. + Mixing E-mail with Babel. + In <em>Network and Distributed Security Symposium (NDSS 96)</em>, + pages 2-16. IEEE, February 1996. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEhintz-pet02" name="hintz-pet02">[29]</a></dt><dd> +A. Hintz. + Fingerprinting websites using traffic analysis. + In R. Dingledine and P. Syverson, editors, <em>Privacy Enhancing + Technologies (PET 2002)</em>, pages 171-178. Springer-Verlag, LNCS 2482, 2002. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEjerichow-jsac98" name="jerichow-jsac98">[30]</a></dt><dd> +A. Jerichow, J. Müller, A. Pfitzmann, B. Pfitzmann, and M. Waidner. + Real-time mixes: A bandwidth-efficient anonymity protocol. + <em>IEEE Journal on Selected Areas in Communications</em>, + 16(4):495-509, May 1998. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITElimits-open" name="limits-open">[31]</a></dt><dd> +D. Kesdogan, D. Agrawal, and S. Penz. + Limits of anonymity in open environments. + In F. Petitcolas, editor, <em>Information Hiding Workshop (IH + 2002)</em>. Springer-Verlag, LNCS 2578, October 2002. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEsocks4" name="socks4">[32]</a></dt><dd> +D. Koblas and M. R. Koblas. + SOCKS. + In <em>UNIX Security III Symposium (1992 USENIX Security + Symposium)</em>, pages 77-83. USENIX, 1992. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEdefensive-dropping" name="defensive-dropping">[33]</a></dt><dd> +B. N. Levine, M. K. Reiter, C. Wang, and M. Wright. + Timing analysis in low-latency mix-based systems. + In A. Juels, editor, <em>Financial Cryptography</em>. Springer-Verlag, + LNCS (forthcoming), 2004. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEhordes-jcs" name="hordes-jcs">[34]</a></dt><dd> +B. N. Levine and C. Shields. + Hordes: A multicast-based protocol for anonymity. + <em>Journal of Computer Security</em>, 10(3):213-240, 2002. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEmeadows96" name="meadows96">[35]</a></dt><dd> +C. Meadows. + The NRL protocol analyzer: An overview. + <em>Journal of Logic Programming</em>, 26(2):113-131, 1996. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEmixmaster-spec" name="mixmaster-spec">[36]</a></dt><dd> +U. Möller, L. Cottrell, P. Palfrader, and L. Sassaman. + Mixmaster Protocol - Version 2. + Draft, July 2003. + <tt><http://www.abditum.com/mixmaster-spec.txt>. + +<div class="p"><!----></div> +</tt></dd> + <dt><a href="#CITEdarkside" name="darkside">[37]</a></dt><dd> +V. S. Pai, L. Wang, K. Park, R. Pang, and L. Peterson. + The Dark Side of the Web: An Open Proxy's View. + <tt><http://codeen.cs.princeton.edu/>. + +<div class="p"><!----></div> +</tt></dd> + <dt><a href="#CITEisdn-mixes" name="isdn-mixes">[38]</a></dt><dd> +A. Pfitzmann, B. Pfitzmann, and M. Waidner. + ISDN-mixes: Untraceable communication with very small bandwidth + overhead. + In <em>GI/ITG Conference on Communication in Distributed Systems</em>, + pages 451-463, February 1991. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEprivoxy" name="privoxy">[39]</a></dt><dd> +Privoxy. + <tt><http://www.privoxy.org/>. + +<div class="p"><!----></div> +</tt></dd> + <dt><a href="#CITEreed-protocols97" name="reed-protocols97">[40]</a></dt><dd> +M. G. Reed, P. F. Syverson, and D. M. Goldschlag. + Protocols using anonymous connections: Mobile applications. + In B. Christianson, B. Crispo, M. Lomas, and M. Roe, editors, <em> + Security Protocols: 5th International Workshop</em>, pages 13-23. + Springer-Verlag, LNCS 1361, April 1997. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEor-jsac98" name="or-jsac98">[41]</a></dt><dd> +M. G. Reed, P. F. Syverson, and D. M. Goldschlag. + Anonymous connections and onion routing. + <em>IEEE Journal on Selected Areas in Communications</em>, + 16(4):482-494, May 1998. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEcrowds-tissec" name="crowds-tissec">[42]</a></dt><dd> +M. K. Reiter and A. D. Rubin. + Crowds: Anonymity for web transactions. + <em>ACM TISSEC</em>, 1(1):66-92, June 1998. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEmorphmix:fc04" name="morphmix:fc04">[43]</a></dt><dd> +M. Rennhard and B. Plattner. + Practical anonymity for the masses with morphmix. + In A. Juels, editor, <em>Financial Cryptography</em>. Springer-Verlag, + LNCS (forthcoming), 2004. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEanonnet" name="anonnet">[44]</a></dt><dd> +M. Rennhard, S. Rafaeli, L. Mathy, B. Plattner, and D. Hutchison. + Analysis of an Anonymity Network for Web Browsing. + In <em>IEEE 7th Intl. Workshop on Enterprise Security (WET ICE + 2002)</em>, Pittsburgh, USA, June 2002. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITESS03" name="SS03">[45]</a></dt><dd> +A. Serjantov and P. Sewell. + Passive attack analysis for connection-based anonymity systems. + In <em>Computer Security - ESORICS 2003</em>. Springer-Verlag, LNCS + 2808, October 2003. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEp5" name="p5">[46]</a></dt><dd> +R. Sherwood, B. Bhattacharjee, and A. Srinivasan. + p<sup>5</sup>: A protocol for scalable anonymous communication. + In <em>IEEE Symposium on Security and Privacy</em>, pages 58-70. IEEE + CS, 2002. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEshsm03" name="shsm03">[47]</a></dt><dd> +A. Shubina and S. Smith. + Using caching for browsing anonymity. + <em>ACM SIGEcom Exchanges</em>, 4(2), Sept 2003. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEor-discex00" name="or-discex00">[48]</a></dt><dd> +P. Syverson, M. Reed, and D. Goldschlag. + Onion Routing access configurations. + In <em>DARPA Information Survivability Conference and Exposition + (DISCEX 2000)</em>, volume 1, pages 34-40. IEEE CS Press, 2000. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEor-pet00" name="or-pet00">[49]</a></dt><dd> +P. Syverson, G. Tsudik, M. Reed, and C. Landwehr. + Towards an Analysis of Onion Routing Security. + In H. Federrath, editor, <em>Designing Privacy Enhancing + Technologies: Workshop on Design Issue in Anonymity and Unobservability</em>, + pages 96-114. Springer-Verlag, LNCS 2009, July 2000. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEtannenbaum96" name="tannenbaum96">[50]</a></dt><dd> +A. Tannenbaum. + Computer networks, 1996. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEjap-backdoor" name="jap-backdoor">[51]</a></dt><dd> +The AN.ON Project. + German police proceeds against anonymity service. + Press release, September 2003. + + <tt><http://www.datenschutzzentrum.de/material/themen/presse/anon-bka_e.htm>. + +<div class="p"><!----></div> +</tt></dd> + <dt><a href="#CITEtangler" name="tangler">[52]</a></dt><dd> +M. Waldman and D. Mazières. + Tangler: A censorship-resistant publishing system based on document + entanglements. + In <em>8<sup>th</sup> ACM Conference on Computer and Communications + Security (CCS-8)</em>, pages 86-135. ACM Press, 2001. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEpublius" name="publius">[53]</a></dt><dd> +M. Waldman, A. Rubin, and L. Cranor. + Publius: A robust, tamper-evident, censorship-resistant and + source-anonymous web publishing system. + In <em>Proc. 9th USENIX Security Symposium</em>, pages 59-72, August + 2000. + +<div class="p"><!----></div> +</dd> + <dt><a href="#CITEwright03" name="wright03">[54]</a></dt><dd> +M. Wright, M. Adler, B. N. Levine, and C. Shields. + Defending anonymous communication against passive logging attacks. + In <em>IEEE Symposium on Security and Privacy</em>, pages 28-41. IEEE + CS, May 2003.</dd> +</dl> + + +<div class="p"><!----></div> +<hr /><h3>Footnotes:</h3> + +<div class="p"><!----></div> +<a name="tthFtNtAAB"></a><a href="#tthFrefAAB"><sup>1</sup></a>Actually, the negotiated key is used to derive two + symmetric keys: one for each direction. +<div class="p"><!----></div> +<a name="tthFtNtAAC"></a><a href="#tthFrefAAC"><sup>2</sup></a> + With 48 bits of digest per cell, the probability of an accidental +collision is far lower than the chance of hardware failure. +<div class="p"><!----></div> +<a name="tthFtNtAAD"></a><a href="#tthFrefAAD"><sup>3</sup></a> +Rather than rely on an external infrastructure, the Onion Routing network +can run the lookup service itself. Our current implementation provides a +simple lookup system on the +directory servers. +<div class="p"><!----></div> +<a name="tthFtNtAAE"></a><a href="#tthFrefAAE"><sup>4</sup></a>Note that this fingerprinting +attack should not be confused with the much more complicated latency +attacks of [<a href="#back01" name="CITEback01">5</a>], which require a fingerprint of the latencies +of all circuits through the network, combined with those from the +network edges to the target user and the responder website. +<br /><br /><hr /><small>File translated from +T<sub><font size="-1">E</font></sub>X +by <a href="http://hutchinson.belmont.ma.us/tth/"> +T<sub><font size="-1">T</font></sub>H</a>, +version 3.59.<br />On 18 May 2004, 10:45.</small> +</body></html> diff --git a/doc/design-paper/tor-design.pdf b/doc/design-paper/tor-design.pdf Binary files differnew file mode 100644 index 0000000000..76a2265153 --- /dev/null +++ b/doc/design-paper/tor-design.pdf diff --git a/doc/design-paper/tor-design.tex b/doc/design-paper/tor-design.tex new file mode 100644 index 0000000000..0a27a92525 --- /dev/null +++ b/doc/design-paper/tor-design.tex @@ -0,0 +1,1988 @@ +\documentclass[twocolumn]{article} +\usepackage{usenix} + +%\documentclass[times,10pt,twocolumn]{article} +%\usepackage{latex8} +%\usepackage{times} +\usepackage{url} +\usepackage{graphics} +\usepackage{amsmath} +\usepackage{epsfig} + +\pagestyle{empty} + +\renewcommand\url{\begingroup \def\UrlLeft{<}\def\UrlRight{>}\urlstyle{tt}\Url} +\newcommand\emailaddr{\begingroup \def\UrlLeft{<}\def\UrlRight{>}\urlstyle{tt}\Url} + +\newcommand{\workingnote}[1]{} % The version that hides the note. +%\newcommand{\workingnote}[1]{(**#1)} % The version that makes the note visible. + +% If an URL ends up with '%'s in it, that's because the line *in the .bib/.tex +% file* is too long, so break it there (it doesn't matter if the next line is +% indented with spaces). -DH + +%\newif\ifpdf +%\ifx\pdfoutput\undefined +% \pdffalse +%\else +% \pdfoutput=1 +% \pdftrue +%\fi + +\newenvironment{tightlist}{\begin{list}{$\bullet$}{ + \setlength{\itemsep}{0mm} + \setlength{\parsep}{0mm} + % \setlength{\labelsep}{0mm} + % \setlength{\labelwidth}{0mm} + % \setlength{\topsep}{0mm} + }}{\end{list}} + +% Cut down on whitespace above and below figures displayed at head/foot of +% page. +\setlength{\textfloatsep}{3mm} +% Cut down on whitespace above and below figures displayed in middle of page +\setlength{\intextsep}{3mm} + +\begin{document} + +%% Use dvipdfm instead. --DH +%\ifpdf +% \pdfcompresslevel=9 +% \pdfpagewidth=\the\paperwidth +% \pdfpageheight=\the\paperheight +%\fi + +\title{Tor: The Second-Generation Onion Router} %\\DRAFT VERSION} +% Putting the 'Private' back in 'Virtual Private Network' + +\author{Roger Dingledine \\ The Free Haven Project \\ arma@freehaven.net \and +Nick Mathewson \\ The Free Haven Project \\ nickm@freehaven.net \and +Paul Syverson \\ Naval Research Lab \\ syverson@itd.nrl.navy.mil} + +\maketitle +\thispagestyle{empty} + +\begin{abstract} +We present Tor, a circuit-based low-latency anonymous communication +service. This second-generation Onion Routing system addresses limitations +in the original design by adding perfect forward secrecy, congestion +control, directory servers, integrity checking, configurable exit policies, +and a practical design for location-hidden services via rendezvous +points. Tor works on the real-world +Internet, requires no special privileges or kernel modifications, requires +little synchronization or coordination between nodes, and provides a +reasonable tradeoff between anonymity, usability, and efficiency. +We briefly describe our experiences with an international network of +more than 30 nodes. % that has been running for several months. +We close with a list of open problems in anonymous communication. +\end{abstract} + +%\begin{center} +%\textbf{Keywords:} anonymity, peer-to-peer, remailer, nymserver, reply block +%\end{center} + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +\section{Overview} +\label{sec:intro} + +Onion Routing is a distributed overlay network designed to anonymize +TCP-based applications like web browsing, secure shell, +and instant messaging. Clients choose a path through the network and +build a \emph{circuit}, in which each node (or ``onion router'' or ``OR'') +in the path knows its predecessor and successor, but no other nodes in +the circuit. Traffic flows down the circuit in fixed-size +\emph{cells}, which are unwrapped by a symmetric key at each node +(like the layers of an onion) and relayed downstream. The +Onion Routing project published several design and analysis +papers \cite{or-ih96,or-jsac98,or-discex00,or-pet00}. While a wide area Onion +Routing network was deployed briefly, the only long-running +public implementation was a fragile +proof-of-concept that ran on a single machine. Even this simple deployment +processed connections from over sixty thousand distinct IP addresses from +all over the world at a rate of about fifty thousand per day. +But many critical design and deployment issues were never +resolved, and the design has not been updated in years. Here +we describe Tor, a protocol for asynchronous, loosely federated onion +routers that provides the following improvements over the old Onion +Routing design: + +\textbf{Perfect forward secrecy:} In the original Onion Routing design, +a single hostile node could record traffic and +later compromise successive nodes in the circuit and force them +to decrypt it. Rather than using a single multiply encrypted data +structure (an \emph{onion}) to lay each circuit, +Tor now uses an incremental or \emph{telescoping} path-building design, +where the initiator negotiates session keys with each successive hop in +the circuit. Once these keys are deleted, subsequently compromised nodes +cannot decrypt old traffic. As a side benefit, onion replay detection +is no longer necessary, and the process of building circuits is more +reliable, since the initiator knows when a hop fails and can then try +extending to a new node. + +\textbf{Separation of ``protocol cleaning'' from anonymity:} +Onion Routing originally required a separate ``application +proxy'' for each supported application protocol---most of which were +never written, so many applications were never supported. Tor uses the +standard and near-ubiquitous SOCKS~\cite{socks4} proxy interface, allowing +us to support most TCP-based programs without modification. Tor now +relies on the filtering features of privacy-enhancing +application-level proxies such as Privoxy~\cite{privoxy}, without trying +to duplicate those features itself. + +\textbf{No mixing, padding, or traffic shaping (yet):} Onion +Routing originally called for batching and reordering cells as they arrived, +assumed padding between ORs, and in +later designs added padding between onion proxies (users) and +ORs~\cite{or-ih96,or-jsac98}. Tradeoffs between padding protection +and cost were discussed, and \emph{traffic shaping} algorithms were +theorized~\cite{or-pet00} to provide good security without expensive +padding, but no concrete padding scheme was suggested. +Recent research~\cite{econymics} +and deployment experience~\cite{freedom21-security} suggest that this +level of resource use is not practical or economical; and even full +link padding is still vulnerable~\cite{defensive-dropping}. Thus, +until we have a proven and convenient design for traffic shaping or +low-latency mixing that improves anonymity against a realistic +adversary, we leave these strategies out. + +\textbf{Many TCP streams can share one circuit:} Onion Routing originally +built a separate circuit for each +application-level request, but this required +multiple public key operations for every request, and also presented +a threat to anonymity from building so many circuits; see +Section~\ref{sec:maintaining-anonymity}. Tor multiplexes multiple TCP +streams along each circuit to improve efficiency and anonymity. + +\textbf{Leaky-pipe circuit topology:} Through in-band signaling +within the circuit, Tor initiators can direct traffic to nodes partway +down the circuit. This novel approach +allows traffic to exit the circuit from the middle---possibly +frustrating traffic shape and volume attacks based on observing the end +of the circuit. (It also allows for long-range padding if +future research shows this to be worthwhile.) + +\textbf{Congestion control:} Earlier anonymity designs do not +address traffic bottlenecks. Unfortunately, typical approaches to +load balancing and flow control in overlay networks involve inter-node +control communication and global views of traffic. Tor's decentralized +congestion control uses end-to-end acks to maintain anonymity +while allowing nodes at the edges of the network to detect congestion +or flooding and send less data until the congestion subsides. + +\textbf{Directory servers:} The earlier Onion Routing design +planned to flood state information through the network---an approach +that can be unreliable and complex. % open to partitioning attacks. +Tor takes a simplified view toward distributing this +information. Certain more trusted nodes act as \emph{directory +servers}: they provide signed directories describing known +routers and their current state. Users periodically download them +via HTTP. + +\textbf{Variable exit policies:} Tor provides a consistent mechanism +for each node to advertise a policy describing the hosts +and ports to which it will connect. These exit policies are critical +in a volunteer-based distributed infrastructure, because each operator +is comfortable with allowing different types of traffic to exit +from his node. + +\textbf{End-to-end integrity checking:} The original Onion Routing +design did no integrity checking on data. Any node on the +circuit could change the contents of data cells as they passed by---for +example, to alter a connection request so it would connect +to a different webserver, or to `tag' encrypted traffic and look for +corresponding corrupted traffic at the network edges~\cite{minion-design}. +Tor hampers these attacks by verifying data integrity before it leaves +the network. + +%\textbf{Improved robustness to failed nodes:} A failed node +%in the old design meant that circuit building failed, but thanks to +%Tor's step-by-step circuit building, users notice failed nodes +%while building circuits and route around them. Additionally, liveness +%information from directories allows users to avoid unreliable nodes in +%the first place. +%% Can't really claim this, now that we've found so many variants of +%% attack on partial-circuit-building. -RD + +\textbf{Rendezvous points and hidden services:} +Tor provides an integrated mechanism for responder anonymity via +location-protected servers. Previous Onion Routing designs included +long-lived ``reply onions'' that could be used to build circuits +to a hidden server, but these reply onions did not provide forward +security, and became useless if any node in the path went down +or rotated its keys. In Tor, clients negotiate {\it rendezvous points} +to connect with hidden servers; reply onions are no longer required. + +Unlike Freedom~\cite{freedom2-arch}, Tor does not require OS kernel +patches or network stack support. This prevents us from anonymizing +non-TCP protocols, but has greatly helped our portability and +deployability. + +%Unlike Freedom~\cite{freedom2-arch}, Tor only anonymizes +%TCP-based protocols---not requiring patches (or built-in support) in an +%operating system's network stack has been valuable to Tor's +%portability and deployability. + +We have implemented all of the above features, including rendezvous +points. Our source code is +available under a free license, and Tor +%, as far as we know, is unencumbered by patents. +is not covered by the patent that affected distribution and use of +earlier versions of Onion Routing. +We have deployed a wide-area alpha network +to test the design, to get more experience with usability +and users, and to provide a research platform for experimentation. +As of this writing, the network stands at 32 nodes %in thirteen +%distinct administrative domains +spread over two continents. + +We review previous work in Section~\ref{sec:related-work}, describe +our goals and assumptions in Section~\ref{sec:assumptions}, +and then address the above list of improvements in +Sections~\ref{sec:design},~\ref{sec:rendezvous}, and~\ref{sec:other-design}. +We summarize +in Section~\ref{sec:attacks} how our design stands up to +known attacks, and talk about our early deployment experiences in +Section~\ref{sec:in-the-wild}. We conclude with a list of open problems in +Section~\ref{sec:maintaining-anonymity} and future work for the Onion +Routing project in Section~\ref{sec:conclusion}. + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +\section{Related work} +\label{sec:related-work} + +Modern anonymity systems date to Chaum's {\bf Mix-Net} +design~\cite{chaum-mix}. Chaum +proposed hiding the correspondence between sender and recipient by +wrapping messages in layers of public-key cryptography, and relaying them +through a path composed of ``mixes.'' Each mix in turn +decrypts, delays, and re-orders messages before relaying them +onward. +%toward their destinations. + +Subsequent relay-based anonymity designs have diverged in two +main directions. Systems like {\bf Babel}~\cite{babel}, +{\bf Mixmaster}~\cite{mixmaster-spec}, +and {\bf Mixminion}~\cite{minion-design} have tried +to maximize anonymity at the cost of introducing comparatively large and +variable latencies. Because of this decision, these \emph{high-latency} +networks resist strong global adversaries, +but introduce too much lag for interactive tasks like web browsing, +Internet chat, or SSH connections. + +Tor belongs to the second category: \emph{low-latency} designs that +try to anonymize interactive network traffic. These systems handle +a variety of bidirectional protocols. They also provide more convenient +mail delivery than the high-latency anonymous email +networks, because the remote mail server provides explicit and timely +delivery confirmation. But because these designs typically +involve many packets that must be delivered quickly, it is +difficult for them to prevent an attacker who can eavesdrop both ends of the +communication from correlating the timing and volume +of traffic entering the anonymity network with traffic leaving it~\cite{SS03}. +These +protocols are similarly vulnerable to an active adversary who introduces +timing patterns into traffic entering the network and looks +for correlated patterns among exiting traffic. +Although some work has been done to frustrate these attacks, most designs +protect primarily against traffic analysis rather than traffic +confirmation (see Section~\ref{subsec:threat-model}). + +The simplest low-latency designs are single-hop proxies such as the +{\bf Anonymizer}~\cite{anonymizer}: a single trusted server strips the +data's origin before relaying it. These designs are easy to +analyze, but users must trust the anonymizing proxy. +Concentrating the traffic to this single point increases the anonymity set +(the people a given user is hiding among), but it is vulnerable if the +adversary can observe all traffic entering and leaving the proxy. + +More complex are distributed-trust, circuit-based anonymizing systems. +In these designs, a user establishes one or more medium-term bidirectional +end-to-end circuits, and tunnels data in fixed-size cells. +Establishing circuits is computationally expensive and typically +requires public-key +cryptography, whereas relaying cells is comparatively inexpensive and +typically requires only symmetric encryption. +Because a circuit crosses several servers, and each server only knows +the adjacent servers in the circuit, no single server can link a +user to her communication partners. + +The {\bf Java Anon Proxy} (also known as JAP or Web MIXes) uses fixed shared +routes known as \emph{cascades}. As with a single-hop proxy, this +approach aggregates users into larger anonymity sets, but again an +attacker only needs to observe both ends of the cascade to bridge all +the system's traffic. The Java Anon Proxy's design +calls for padding between end users and the head of the +cascade~\cite{web-mix}. However, it is not demonstrated whether the current +implementation's padding policy improves anonymity. + +{\bf PipeNet}~\cite{back01, pipenet}, another low-latency design proposed +around the same time as Onion Routing, gave +stronger anonymity but allowed a single user to shut +down the network by not sending. Systems like {\bf ISDN +mixes}~\cite{isdn-mixes} were designed for other environments with +different assumptions. +%XXX please can we fix this sentence to something less demeaning + +In P2P designs like {\bf Tarzan}~\cite{tarzan:ccs02} and +{\bf MorphMix}~\cite{morphmix:fc04}, all participants both generate +traffic and relay traffic for others. These systems aim to conceal +whether a given peer originated a request +or just relayed it from another peer. While Tarzan and MorphMix use +layered encryption as above, {\bf Crowds}~\cite{crowds-tissec} simply assumes +an adversary who cannot observe the initiator: it uses no public-key +encryption, so any node on a circuit can read users' traffic. + +{\bf Hordes}~\cite{hordes-jcs} is based on Crowds but also uses multicast +responses to hide the initiator. {\bf Herbivore}~\cite{herbivore} and +$\mbox{\bf P}^{\mathbf 5}$~\cite{p5} go even further, requiring broadcast. +These systems are designed primarily for communication among peers, +although Herbivore users can make external connections by +requesting a peer to serve as a proxy. + +Systems like {\bf Freedom} and the original Onion Routing build circuits +all at once, using a layered ``onion'' of public-key encrypted messages, +each layer of which provides session keys and the address of the +next server in the circuit. Tor as described herein, Tarzan, MorphMix, +{\bf Cebolla}~\cite{cebolla}, and Rennhard's {\bf Anonymity Network}~\cite{anonnet} +build circuits +in stages, extending them one hop at a time. +Section~\ref{subsubsec:constructing-a-circuit} describes how this +approach enables perfect forward secrecy. + +Circuit-based designs must choose which protocol layer +to anonymize. They may intercept IP packets directly, and +relay them whole (stripping the source address) along the +circuit~\cite{freedom2-arch,tarzan:ccs02}. Like +Tor, they may accept TCP streams and relay the data in those streams, +ignoring the breakdown of that data into TCP +segments~\cite{morphmix:fc04,anonnet}. Finally, like Crowds, they may accept +application-level protocols such as HTTP and relay the application +requests themselves. +Making this protocol-layer decision requires a compromise between flexibility +and anonymity. For example, a system that understands HTTP +can strip +identifying information from requests, can take advantage of caching +to limit the number of requests that leave the network, and can batch +or encode requests to minimize the number of connections. +On the other hand, an IP-level anonymizer can handle nearly any protocol, +even ones unforeseen by its designers (though these systems require +kernel-level modifications to some operating systems, and so are more +complex and less portable). TCP-level anonymity networks like Tor present +a middle approach: they are application neutral (so long as the +application supports, or can be tunneled across, TCP), but by treating +application connections as data streams rather than raw TCP packets, +they avoid the inefficiencies of tunneling TCP over +TCP. + +Distributed-trust anonymizing systems need to prevent attackers from +adding too many servers and thus compromising user paths. +Tor relies on a small set of well-known directory servers, run by +independent parties, to decide which nodes can +join. Tarzan and MorphMix allow unknown users to run servers, and use +a limited resource (like IP addresses) to prevent an attacker from +controlling too much of the network. Crowds suggests requiring +written, notarized requests from potential crowd members. + +Anonymous communication is essential for censorship-resistant +systems like Eternity~\cite{eternity}, Free~Haven~\cite{freehaven-berk}, +Publius~\cite{publius}, and Tangler~\cite{tangler}. Tor's rendezvous +points enable connections between mutually anonymous entities; they +are a building block for location-hidden servers, which are needed by +Eternity and Free~Haven. + +% didn't include rewebbers. No clear place to put them, so I'll leave +% them out for now. -RD + +\section{Design goals and assumptions} +\label{sec:assumptions} + +\noindent{\large\bf Goals}\\ +Like other low-latency anonymity designs, Tor seeks to frustrate +attackers from linking communication partners, or from linking +multiple communications to or from a single user. Within this +main goal, however, several considerations have directed +Tor's evolution. + +\textbf{Deployability:} The design must be deployed and used in the +real world. Thus it +must not be expensive to run (for example, by requiring more bandwidth +than volunteers are willing to provide); must not place a heavy +liability burden on operators (for example, by allowing attackers to +implicate onion routers in illegal activities); and must not be +difficult or expensive to implement (for example, by requiring kernel +patches, or separate proxies for every protocol). We also cannot +require non-anonymous parties (such as websites) +to run our software. (Our rendezvous point design does not meet +this goal for non-anonymous users talking to hidden servers, +however; see Section~\ref{sec:rendezvous}.) + +\textbf{Usability:} A hard-to-use system has fewer users---and because +anonymity systems hide users among users, a system with fewer users +provides less anonymity. Usability is thus not only a convenience: +it is a security requirement~\cite{econymics,back01}. Tor should +therefore not +require modifying familiar applications; should not introduce prohibitive +delays; +and should require as few configuration decisions +as possible. Finally, Tor should be easily implementable on all common +platforms; we cannot require users to change their operating system +to be anonymous. (Tor currently runs on Win32, Linux, +Solaris, BSD-style Unix, MacOS X, and probably others.) + +\textbf{Flexibility:} The protocol must be flexible and well-specified, +so Tor can serve as a test-bed for future research. +Many of the open problems in low-latency anonymity +networks, such as generating dummy traffic or preventing Sybil +attacks~\cite{sybil}, may be solvable independently from the issues +solved by +Tor. Hopefully future systems will not need to reinvent Tor's design. +%(But note that while a flexible design benefits researchers, +%there is a danger that differing choices of extensions will make users +%distinguishable. Experiments should be run on a separate network.) + +\textbf{Simple design:} The protocol's design and security +parameters must be well-understood. Additional features impose implementation +and complexity costs; adding unproven techniques to the design threatens +deployability, readability, and ease of security analysis. Tor aims to +deploy a simple and stable system that integrates the best accepted +approaches to protecting anonymity.\\ + +\noindent{\large\bf Non-goals}\label{subsec:non-goals}\\ +In favoring simple, deployable designs, we have explicitly deferred +several possible goals, either because they are solved elsewhere, or because +they are not yet solved. + +\textbf{Not peer-to-peer:} Tarzan and MorphMix aim to scale to completely +decentralized peer-to-peer environments with thousands of short-lived +servers, many of which may be controlled by an adversary. This approach +is appealing, but still has many open +problems~\cite{tarzan:ccs02,morphmix:fc04}. + +\textbf{Not secure against end-to-end attacks:} Tor does not claim +to completely solve end-to-end timing or intersection +attacks. Some approaches, such as having users run their own onion routers, +may help; +see Section~\ref{sec:maintaining-anonymity} for more discussion. + +\textbf{No protocol normalization:} Tor does not provide \emph{protocol +normalization} like Privoxy or the Anonymizer. If senders want anonymity from +responders while using complex and variable +protocols like HTTP, Tor must be layered with a filtering proxy such +as Privoxy to hide differences between clients, and expunge protocol +features that leak identity. +Note that by this separation Tor can also provide services that +are anonymous to the network yet authenticated to the responder, like +SSH. Similarly, Tor does not integrate +tunneling for non-stream-based protocols like UDP; this must be +provided by an external service if appropriate. + +\textbf{Not steganographic:} Tor does not try to conceal who is connected +to the network. + +\subsection{Threat Model} +\label{subsec:threat-model} + +A global passive adversary is the most commonly assumed threat when +analyzing theoretical anonymity designs. But like all practical +low-latency systems, Tor does not protect against such a strong +adversary. Instead, we assume an adversary who can observe some fraction +of network traffic; who can generate, modify, delete, or delay +traffic; who can operate onion routers of his own; and who can +compromise some fraction of the onion routers. + +In low-latency anonymity systems that use layered encryption, the +adversary's typical goal is to observe both the initiator and the +responder. By observing both ends, passive attackers can confirm a +suspicion that Alice is +talking to Bob if the timing and volume patterns of the traffic on the +connection are distinct enough; active attackers can induce timing +signatures on the traffic to force distinct patterns. Rather +than focusing on these \emph{traffic confirmation} attacks, +we aim to prevent \emph{traffic +analysis} attacks, where the adversary uses traffic patterns to learn +which points in the network he should attack. + +Our adversary might try to link an initiator Alice with her +communication partners, or try to build a profile of Alice's +behavior. He might mount passive attacks by observing the network edges +and correlating traffic entering and leaving the network---by +relationships in packet timing, volume, or externally visible +user-selected +options. The adversary can also mount active attacks by compromising +routers or keys; by replaying traffic; by selectively denying service +to trustworthy routers to move users to +compromised routers, or denying service to users to see if traffic +elsewhere in the +network stops; or by introducing patterns into traffic that can later be +detected. The adversary might subvert the directory servers to give users +differing views of network state. Additionally, he can try to decrease +the network's reliability by attacking nodes or by performing antisocial +activities from reliable nodes and trying to get them taken down---making +the network unreliable flushes users to other less anonymous +systems, where they may be easier to attack. We summarize +in Section~\ref{sec:attacks} how well the Tor design defends against +each of these attacks. + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +\section{The Tor Design} +\label{sec:design} + +The Tor network is an overlay network; each onion router (OR) +runs as a normal +user-level process without any special privileges. +Each onion router maintains a TLS~\cite{TLS} +connection to every other onion router. +%(We discuss alternatives to this clique-topology assumption in +%Section~\ref{sec:maintaining-anonymity}.) +% A subset of the ORs also act as +%directory servers, tracking which routers are in the network; +%see Section~\ref{subsec:dirservers} for directory server details. +Each user +runs local software called an onion proxy (OP) to fetch directories, +establish circuits across the network, +and handle connections from user applications. These onion proxies accept +TCP streams and multiplex them across the circuits. The onion +router on the other side +of the circuit connects to the requested destinations +and relays data. + +Each onion router maintains a long-term identity key and a short-term +onion key. The identity +key is used to sign TLS certificates, to sign the OR's \emph{router +descriptor} (a summary of its keys, address, bandwidth, exit policy, +and so on), and (by directory servers) to sign directories. %Changing +%the identity key of a router is considered equivalent to creating a +%new router. +The onion key is used to decrypt requests +from users to set up a circuit and negotiate ephemeral keys. +The TLS protocol also establishes a short-term link key when communicating +between ORs. Short-term keys are rotated periodically and +independently, to limit the impact of key compromise. + +Section~\ref{subsec:cells} presents the fixed-size +\emph{cells} that are the unit of communication in Tor. We describe +in Section~\ref{subsec:circuits} how circuits are +built, extended, truncated, and destroyed. Section~\ref{subsec:tcp} +describes how TCP streams are routed through the network. We address +integrity checking in Section~\ref{subsec:integrity-checking}, +and resource limiting in Section~\ref{subsec:rate-limit}. +Finally, +Section~\ref{subsec:congestion} talks about congestion control and +fairness issues. + +\subsection{Cells} +\label{subsec:cells} + +Onion routers communicate with one another, and with users' OPs, via +TLS connections with ephemeral keys. Using TLS conceals the data on +the connection with perfect forward secrecy, and prevents an attacker +from modifying data on the wire or impersonating an OR. + +Traffic passes along these connections in fixed-size cells. Each cell +is 512 bytes, %(but see Section~\ref{sec:conclusion} for a discussion of +%allowing large cells and small cells on the same network), +and consists of a header and a payload. The header includes a circuit +identifier (circID) that specifies which circuit the cell refers to +(many circuits can be multiplexed over the single TLS connection), and +a command to describe what to do with the cell's payload. (Circuit +identifiers are connection-specific: each circuit has a different +circID on each OP/OR or OR/OR connection it traverses.) +Based on their command, cells are either \emph{control} cells, which are +always interpreted by the node that receives them, or \emph{relay} cells, +which carry end-to-end stream data. The control cell commands are: +\emph{padding} (currently used for keepalive, but also usable for link +padding); \emph{create} or \emph{created} (used to set up a new circuit); +and \emph{destroy} (to tear down a circuit). + +Relay cells have an additional header (the relay header) at the front +of the payload, containing a streamID (stream identifier: many streams can +be multiplexed over a circuit); an end-to-end checksum for integrity +checking; the length of the relay payload; and a relay command. +The entire contents of the relay header and the relay cell payload +are encrypted or decrypted together as the relay cell moves along the +circuit, using the 128-bit AES cipher in counter mode to generate a +cipher stream. The relay commands are: \emph{relay +data} (for data flowing down the stream), \emph{relay begin} (to open a +stream), \emph{relay end} (to close a stream cleanly), \emph{relay +teardown} (to close a broken stream), \emph{relay connected} +(to notify the OP that a relay begin has succeeded), \emph{relay +extend} and \emph{relay extended} (to extend the circuit by a hop, +and to acknowledge), \emph{relay truncate} and \emph{relay truncated} +(to tear down only part of the circuit, and to acknowledge), \emph{relay +sendme} (used for congestion control), and \emph{relay drop} (used to +implement long-range dummies). +We give a visual overview of cell structure plus the details of relay +cell structure, and then describe each of these cell types and commands +in more detail below. + +%\begin{figure}[h] +%\unitlength=1cm +%\centering +%\begin{picture}(8.0,1.5) +%\put(4,.5){\makebox(0,0)[c]{\epsfig{file=cell-struct,width=7cm}}} +%\end{picture} +%\end{figure} + +\begin{figure}[h] +\centering +\mbox{\epsfig{figure=cell-struct,width=7cm}} +\end{figure} + +\subsection{Circuits and streams} +\label{subsec:circuits} + +Onion Routing originally built one circuit for each +TCP stream. Because building a circuit can take several tenths of a +second (due to public-key cryptography and network latency), +this design imposed high costs on applications like web browsing that +open many TCP streams. + +In Tor, each circuit can be shared by many TCP streams. To avoid +delays, users construct circuits preemptively. To limit linkability +among their streams, users' OPs build a new circuit +periodically if the previous ones have been used, +and expire old used circuits that no longer have any open streams. +OPs consider rotating to a new circuit once a minute: thus +even heavy users spend negligible time +building circuits, but a limited number of requests can be linked +to each other through a given exit node. Also, because circuits are built +in the background, OPs can recover from failed circuit creation +without harming user experience.\\ + +\begin{figure}[h] +\centering +\mbox{\epsfig{figure=interaction,width=8.75cm}} +\caption{Alice builds a two-hop circuit and begins fetching a web page.} +\label{fig:interaction} +\end{figure} + +\noindent{\large\bf Constructing a circuit}\label{subsubsec:constructing-a-circuit}\\ +%\subsubsection{Constructing a circuit} +A user's OP constructs circuits incrementally, negotiating a +symmetric key with each OR on the circuit, one hop at a time. To begin +creating a new circuit, the OP (call her Alice) sends a +\emph{create} cell to the first node in her chosen path (call him Bob). +(She chooses a new +circID $C_{AB}$ not currently used on the connection from her to Bob.) +The \emph{create} cell's +payload contains the first half of the Diffie-Hellman handshake +($g^x$), encrypted to the onion key of the OR (call him Bob). Bob +responds with a \emph{created} cell containing $g^y$ +along with a hash of the negotiated key $K=g^{xy}$. + +Once the circuit has been established, Alice and Bob can send one +another relay cells encrypted with the negotiated +key.\footnote{Actually, the negotiated key is used to derive two + symmetric keys: one for each direction.} More detail is given in +the next section. + +To extend the circuit further, Alice sends a \emph{relay extend} cell +to Bob, specifying the address of the next OR (call her Carol), and +an encrypted $g^{x_2}$ for her. Bob copies the half-handshake into a +\emph{create} cell, and passes it to Carol to extend the circuit. +(Bob chooses a new circID $C_{BC}$ not currently used on the connection +between him and Carol. Alice never needs to know this circID; only Bob +associates $C_{AB}$ on his connection with Alice to $C_{BC}$ on +his connection with Carol.) +When Carol responds with a \emph{created} cell, Bob wraps the payload +into a \emph{relay extended} cell and passes it back to Alice. Now +the circuit is extended to Carol, and Alice and Carol share a common key +$K_2 = g^{x_2 y_2}$. + +To extend the circuit to a third node or beyond, Alice +proceeds as above, always telling the last node in the circuit to +extend one hop further. + +This circuit-level handshake protocol achieves unilateral entity +authentication (Alice knows she's handshaking with the OR, but +the OR doesn't care who is opening the circuit---Alice uses no public key +and remains anonymous) and unilateral key authentication +(Alice and the OR agree on a key, and Alice knows only the OR learns +it). It also achieves forward +secrecy and key freshness. More formally, the protocol is as follows +(where $E_{PK_{Bob}}(\cdot)$ is encryption with Bob's public key, +$H$ is a secure hash function, and $|$ is concatenation): +\begin{equation*} +\begin{aligned} +\mathrm{Alice} \rightarrow \mathrm{Bob}&: E_{PK_{Bob}}(g^x) \\ +\mathrm{Bob} \rightarrow \mathrm{Alice}&: g^y, H(K | \mathrm{``handshake"}) \\ +\end{aligned} +\end{equation*} + +\noindent In the second step, Bob proves that it was he who received $g^x$, +and who chose $y$. We use PK encryption in the first step +(rather than, say, using the first two steps of STS, which has a +signature in the second step) because a single cell is too small to +hold both a public key and a signature. Preliminary analysis with the +NRL protocol analyzer~\cite{meadows96} shows this protocol to be +secure (including perfect forward secrecy) under the +traditional Dolev-Yao model.\\ + +\noindent{\large\bf Relay cells}\\ +%\subsubsection{Relay cells} +% +Once Alice has established the circuit (so she shares keys with each +OR on the circuit), she can send relay cells. +%Recall that every relay cell has a streamID that indicates to which +%stream the cell belongs. %This streamID allows a relay cell to be +%addressed to any OR on the circuit. +Upon receiving a relay +cell, an OR looks up the corresponding circuit, and decrypts the relay +header and payload with the session key for that circuit. +If the cell is headed away from Alice the OR then checks whether the +decrypted cell has a valid digest (as an optimization, the first +two bytes of the integrity check are zero, so in most cases we can avoid +computing the hash). +%is recognized---either because it +%corresponds to an open stream at this OR for the given circuit, or because +%it is the control streamID (zero). +If valid, it accepts the relay cell and processes it as described +below. Otherwise, +the OR looks up the circID and OR for the +next step in the circuit, replaces the circID as appropriate, and +sends the decrypted relay cell to the next OR. (If the OR at the end +of the circuit receives an unrecognized relay cell, an error has +occurred, and the circuit is torn down.) + +OPs treat incoming relay cells similarly: they iteratively unwrap the +relay header and payload with the session keys shared with each +OR on the circuit, from the closest to farthest. +If at any stage the digest is valid, the cell must have +originated at the OR whose encryption has just been removed. + +To construct a relay cell addressed to a given OR, Alice assigns the +digest, and then iteratively +encrypts the cell payload (that is, the relay header and payload) with +the symmetric key of each hop up to that OR. Because the digest is +encrypted to a different value at each step, only at the targeted OR +will it have a meaningful value.\footnote{ + % Should we just say that 2^56 is itself negligible? + % Assuming 4-hop circuits with 10 streams per hop, there are 33 + % possible bad streamIDs before the last circuit. This still + % gives an error only once every 2 million terabytes (approx). +With 48 bits of digest per cell, the probability of an accidental +collision is far lower than the chance of hardware failure.} +This \emph{leaky pipe} circuit topology +allows Alice's streams to exit at different ORs on a single circuit. +Alice may choose different exit points because of their exit policies, +or to keep the ORs from knowing that two streams +originate from the same person. + +When an OR later replies to Alice with a relay cell, it +encrypts the cell's relay header and payload with the single key it +shares with Alice, and sends the cell back toward Alice along the +circuit. Subsequent ORs add further layers of encryption as they +relay the cell back to Alice. + +To tear down a circuit, Alice sends a \emph{destroy} control +cell. Each OR in the circuit receives the \emph{destroy} cell, closes +all streams on that circuit, and passes a new \emph{destroy} cell +forward. But just as circuits are built incrementally, they can also +be torn down incrementally: Alice can send a \emph{relay +truncate} cell to a single OR on a circuit. That OR then sends a +\emph{destroy} cell forward, and acknowledges with a +\emph{relay truncated} cell. Alice can then extend the circuit to +different nodes, without signaling to the intermediate nodes (or +a limited observer) that she has changed her circuit. +Similarly, if a node on the circuit goes down, the adjacent +node can send a \emph{relay truncated} cell back to Alice. Thus the +``break a node and see which circuits go down'' +attack~\cite{freedom21-security} is weakened. + +\subsection{Opening and closing streams} +\label{subsec:tcp} + +When Alice's application wants a TCP connection to a given +address and port, it asks the OP (via SOCKS) to make the +connection. The OP chooses the newest open circuit (or creates one if +needed), and chooses a suitable OR on that circuit to be the +exit node (usually the last node, but maybe others due to exit policy +conflicts; see Section~\ref{subsec:exitpolicies}.) The OP then opens +the stream by sending a \emph{relay begin} cell to the exit node, +using a new random streamID. Once the +exit node connects to the remote host, it responds +with a \emph{relay connected} cell. Upon receipt, the OP sends a +SOCKS reply to notify the application of its success. The OP +now accepts data from the application's TCP stream, packaging it into +\emph{relay data} cells and sending those cells along the circuit to +the chosen OR. + +There's a catch to using SOCKS, however---some applications pass the +alphanumeric hostname to the Tor client, while others resolve it into +an IP address first and then pass the IP address to the Tor client. If +the application does DNS resolution first, Alice thereby reveals her +destination to the remote DNS server, rather than sending the hostname +through the Tor network to be resolved at the far end. Common applications +like Mozilla and SSH have this flaw. + +With Mozilla, the flaw is easy to address: the filtering HTTP +proxy called Privoxy gives a hostname to the Tor client, so Alice's +computer never does DNS resolution. +But a portable general solution, such as is needed for +SSH, is +an open problem. Modifying or replacing the local nameserver +can be invasive, brittle, and unportable. Forcing the resolver +library to prefer TCP rather than UDP is hard, and also has +portability problems. Dynamically intercepting system calls to the +resolver library seems a promising direction. We could also provide +a tool similar to \emph{dig} to perform a private lookup through the +Tor network. Currently, we encourage the use of privacy-aware proxies +like Privoxy wherever possible. + +Closing a Tor stream is analogous to closing a TCP stream: it uses a +two-step handshake for normal operation, or a one-step handshake for +errors. If the stream closes abnormally, the adjacent node simply sends a +\emph{relay teardown} cell. If the stream closes normally, the node sends +a \emph{relay end} cell down the circuit, and the other side responds with +its own \emph{relay end} cell. Because +all relay cells use layered encryption, only the destination OR knows +that a given relay cell is a request to close a stream. This two-step +handshake allows Tor to support TCP-based applications that use half-closed +connections. +% such as broken HTTP clients that close their side of the +%stream after writing but are still willing to read. + +\subsection{Integrity checking on streams} +\label{subsec:integrity-checking} + +Because the old Onion Routing design used a stream cipher without integrity +checking, traffic was +vulnerable to a malleability attack: though the attacker could not +decrypt cells, any changes to encrypted data +would create corresponding changes to the data leaving the network. +This weakness allowed an adversary who could guess the encrypted content +to change a padding cell to a destroy +cell; change the destination address in a \emph{relay begin} cell to the +adversary's webserver; or change an FTP command from +{\tt dir} to {\tt rm~*}. (Even an external +adversary could do this, because the link encryption similarly used a +stream cipher.) + +Because Tor uses TLS on its links, external adversaries cannot modify +data. Addressing the insider malleability attack, however, is +more complex. + +We could do integrity checking of the relay cells at each hop, either +by including hashes or by using an authenticating cipher mode like +EAX~\cite{eax}, but there are some problems. First, these approaches +impose a message-expansion overhead at each hop, and so we would have to +either leak the path length or waste bytes by padding to a maximum +path length. Second, these solutions can only verify traffic coming +from Alice: ORs would not be able to produce suitable hashes for +the intermediate hops, since the ORs on a circuit do not know the +other ORs' session keys. Third, we have already accepted that our design +is vulnerable to end-to-end timing attacks; so tagging attacks performed +within the circuit provide no additional information to the attacker. + +Thus, we check integrity only at the edges of each stream. (Remember that +in our leaky-pipe circuit topology, a stream's edge could be any hop +in the circuit.) When Alice +negotiates a key with a new hop, they each initialize a SHA-1 +digest with a derivative of that key, +thus beginning with randomness that only the two of them know. +Then they each incrementally add to the SHA-1 digest the contents of +all relay cells they create, and include with each relay cell the +first four bytes of the current digest. Each also keeps a SHA-1 +digest of data received, to verify that the received hashes are correct. + +To be sure of removing or modifying a cell, the attacker must be able +to deduce the current digest state (which depends on all +traffic between Alice and Bob, starting with their negotiated key). +Attacks on SHA-1 where the adversary can incrementally add to a hash +to produce a new valid hash don't work, because all hashes are +end-to-end encrypted across the circuit. The computational overhead +of computing the digests is minimal compared to doing the AES +encryption performed at each hop of the circuit. We use only four +bytes per cell to minimize overhead; the chance that an adversary will +correctly guess a valid hash +%, plus the payload the current cell, +is +acceptably low, given that the OP or OR tear down the circuit if they +receive a bad hash. + +\subsection{Rate limiting and fairness} +\label{subsec:rate-limit} + +Volunteers are more willing to run services that can limit +their bandwidth usage. To accommodate them, Tor servers use a +token bucket approach~\cite{tannenbaum96} to +enforce a long-term average rate of incoming bytes, while still +permitting short-term bursts above the allowed bandwidth. +% Current bucket sizes are set to ten seconds' worth of traffic. + +%Further, we want to avoid starving any Tor streams. Entire circuits +%could starve if we read greedily from connections and one connection +%uses all the remaining bandwidth. We solve this by dividing the number +%of tokens in the bucket by the number of connections that want to read, +%and reading at most that number of bytes from each connection. We iterate +%this procedure until the number of tokens in the bucket is under some +%threshold (currently 10KB), at which point we greedily read from connections. + +Because the Tor protocol outputs about the same number of bytes as it +takes in, it is sufficient in practice to limit only incoming bytes. +With TCP streams, however, the correspondence is not one-to-one: +relaying a single incoming byte can require an entire 512-byte cell. +(We can't just wait for more bytes, because the local application may +be awaiting a reply.) Therefore, we treat this case as if the entire +cell size had been read, regardless of the cell's fullness. + +Further, inspired by Rennhard et al's design in~\cite{anonnet}, a +circuit's edges can heuristically distinguish interactive streams from bulk +streams by comparing the frequency with which they supply cells. We can +provide good latency for interactive streams by giving them preferential +service, while still giving good overall throughput to the bulk +streams. Such preferential treatment presents a possible end-to-end +attack, but an adversary observing both +ends of the stream can already learn this information through timing +attacks. + +\subsection{Congestion control} +\label{subsec:congestion} + +Even with bandwidth rate limiting, we still need to worry about +congestion, either accidental or intentional. If enough users choose the +same OR-to-OR connection for their circuits, that connection can become +saturated. For example, an attacker could send a large file +through the Tor network to a webserver he runs, and then +refuse to read any of the bytes at the webserver end of the +circuit. Without some congestion control mechanism, these bottlenecks +can propagate back through the entire network. We don't need to +reimplement full TCP windows (with sequence numbers, +the ability to drop cells when we're full and retransmit later, and so +on), +because TCP already guarantees in-order delivery of each +cell. +%But we need to investigate further the effects of the current +%parameters on throughput and latency, while also keeping privacy in mind; +%see Section~\ref{sec:maintaining-anonymity} for more discussion. +We describe our response below. + +\textbf{Circuit-level throttling:} +To control a circuit's bandwidth usage, each OR keeps track of two +windows. The \emph{packaging window} tracks how many relay data cells the OR is +allowed to package (from incoming TCP streams) for transmission back to the OP, +and the \emph{delivery window} tracks how many relay data cells it is willing +to deliver to TCP streams outside the network. Each window is initialized +(say, to 1000 data cells). When a data cell is packaged or delivered, +the appropriate window is decremented. When an OR has received enough +data cells (currently 100), it sends a \emph{relay sendme} cell towards the OP, +with streamID zero. When an OR receives a \emph{relay sendme} cell with +streamID zero, it increments its packaging window. Either of these cells +increments the corresponding window by 100. If the packaging window +reaches 0, the OR stops reading from TCP connections for all streams +on the corresponding circuit, and sends no more relay data cells until +receiving a \emph{relay sendme} cell. + +The OP behaves identically, except that it must track a packaging window +and a delivery window for every OR in the circuit. If a packaging window +reaches 0, it stops reading from streams destined for that OR. + +\textbf{Stream-level throttling}: +The stream-level congestion control mechanism is similar to the +circuit-level mechanism. ORs and OPs use \emph{relay sendme} cells +to implement end-to-end flow control for individual streams across +circuits. Each stream begins with a packaging window (currently 500 cells), +and increments the window by a fixed value (50) upon receiving a \emph{relay +sendme} cell. Rather than always returning a \emph{relay sendme} cell as soon +as enough cells have arrived, the stream-level congestion control also +has to check whether data has been successfully flushed onto the TCP +stream; it sends the \emph{relay sendme} cell only when the number of bytes pending +to be flushed is under some threshold (currently 10 cells' worth). + +%% Maybe omit this next paragraph. -NM +%Currently, non-data relay cells do not affect the windows. Thus we +%avoid potential deadlock issues, for example, arising because a stream +%can't send a \emph{relay sendme} cell when its packaging window is empty. + +These arbitrarily chosen parameters seem to give tolerable throughput +and delay; see Section~\ref{sec:in-the-wild}. + +\section{Rendezvous Points and hidden services} +\label{sec:rendezvous} + +Rendezvous points are a building block for \emph{location-hidden +services} (also known as \emph{responder anonymity}) in the Tor +network. Location-hidden services allow Bob to offer a TCP +service, such as a webserver, without revealing his IP address. +This type of anonymity protects against distributed DoS attacks: +attackers are forced to attack the onion routing network +because they do not know Bob's IP address. + +Our design for location-hidden servers has the following goals. +\textbf{Access-control:} Bob needs a way to filter incoming requests, +so an attacker cannot flood Bob simply by making many connections to him. +\textbf{Robustness:} Bob should be able to maintain a long-term pseudonymous +identity even in the presence of router failure. Bob's service must +not be tied to a single OR, and Bob must be able to migrate his service +across ORs. \textbf{Smear-resistance:} +A social attacker +should not be able to ``frame'' a rendezvous router by +offering an illegal or disreputable location-hidden service and +making observers believe the router created that service. +\textbf{Application-transparency:} Although we require users +to run special software to access location-hidden servers, we must not +require them to modify their applications. + +We provide location-hiding for Bob by allowing him to advertise +several onion routers (his \emph{introduction points}) as contact +points. He may do this on any robust efficient +key-value lookup system with authenticated updates, such as a +distributed hash table (DHT) like CFS~\cite{cfs:sosp01}.\footnote{ +Rather than rely on an external infrastructure, the Onion Routing network +can run the lookup service itself. Our current implementation provides a +simple lookup system on the +directory servers.} Alice, the client, chooses an OR as her +\emph{rendezvous point}. She connects to one of Bob's introduction +points, informs him of her rendezvous point, and then waits for him +to connect to the rendezvous point. This extra level of indirection +helps Bob's introduction points avoid problems associated with serving +unpopular files directly (for example, if Bob serves +material that the introduction point's community finds objectionable, +or if Bob's service tends to get attacked by network vandals). +The extra level of indirection also allows Bob to respond to some requests +and ignore others. + +\subsection{Rendezvous points in Tor} + +The following steps are +%We give an overview of the steps of a rendezvous. These are +performed on behalf of Alice and Bob by their local OPs; +application integration is described more fully below. + +\begin{tightlist} +\item Bob generates a long-term public key pair to identify his service. +\item Bob chooses some introduction points, and advertises them on + the lookup service, signing the advertisement with his public key. He + can add more later. +\item Bob builds a circuit to each of his introduction points, and tells + them to wait for requests. +\item Alice learns about Bob's service out of band (perhaps Bob told her, + or she found it on a website). She retrieves the details of Bob's + service from the lookup service. If Alice wants to access Bob's + service anonymously, she must connect to the lookup service via Tor. +\item Alice chooses an OR as the rendezvous point (RP) for her connection to + Bob's service. She builds a circuit to the RP, and gives it a + randomly chosen ``rendezvous cookie'' to recognize Bob. +\item Alice opens an anonymous stream to one of Bob's introduction + points, and gives it a message (encrypted with Bob's public key) + telling it about herself, + her RP and rendezvous cookie, and the + start of a DH + handshake. The introduction point sends the message to Bob. +\item If Bob wants to talk to Alice, he builds a circuit to Alice's + RP and sends the rendezvous cookie, the second half of the DH + handshake, and a hash of the session + key they now share. By the same argument as in + Section~\ref{subsubsec:constructing-a-circuit}, Alice knows she + shares the key only with Bob. +\item The RP connects Alice's circuit to Bob's. Note that RP can't + recognize Alice, Bob, or the data they transmit. +\item Alice sends a \emph{relay begin} cell along the circuit. It + arrives at Bob's OP, which connects to Bob's + webserver. +\item An anonymous stream has been established, and Alice and Bob + communicate as normal. +\end{tightlist} + +When establishing an introduction point, Bob provides the onion router +with the public key identifying his service. Bob signs his +messages, so others cannot usurp his introduction point +in the future. He uses the same public key to establish the other +introduction points for his service, and periodically refreshes his +entry in the lookup service. + +The message that Alice gives +the introduction point includes a hash of Bob's public key % to identify +%the service, along with +and an optional initial authorization token (the +introduction point can do prescreening, for example to block replays). Her +message to Bob may include an end-to-end authorization token so Bob +can choose whether to respond. +The authorization tokens can be used to provide selective access: +important users can get uninterrupted access. +%important users get tokens to ensure uninterrupted access. %to the +%service. +During normal situations, Bob's service might simply be offered +directly from mirrors, while Bob gives out tokens to high-priority users. If +the mirrors are knocked down, +%by distributed DoS attacks or even +%physical attack, +those users can switch to accessing Bob's service via +the Tor rendezvous system. + +Bob's introduction points are themselves subject to DoS---he must +open many introduction points or risk such an attack. +He can provide selected users with a current list or future schedule of +unadvertised introduction points; +this is most practical +if there is a stable and large group of introduction points +available. Bob could also give secret public keys +for consulting the lookup service. All of these approaches +limit exposure even when +some selected users collude in the DoS\@. + +\subsection{Integration with user applications} + +Bob configures his onion proxy to know the local IP address and port of his +service, a strategy for authorizing clients, and his public key. The onion +proxy anonymously publishes a signed statement of Bob's +public key, an expiration time, and +the current introduction points for his service onto the lookup service, +indexed +by the hash of his public key. Bob's webserver is unmodified, +and doesn't even know that it's hidden behind the Tor network. + +Alice's applications also work unchanged---her client interface +remains a SOCKS proxy. We encode all of the necessary information +into the fully qualified domain name (FQDN) Alice uses when establishing her +connection. Location-hidden services use a virtual top level domain +called {\tt .onion}: thus hostnames take the form {\tt x.y.onion} where +{\tt x} is the authorization cookie and {\tt y} encodes the hash of +the public key. Alice's onion proxy +examines addresses; if they're destined for a hidden server, it decodes +the key and starts the rendezvous as described above. + +\subsection{Previous rendezvous work} +%XXXX Should this get integrated into the earlier related work section? -NM + +Rendezvous points in low-latency anonymity systems were first +described for use in ISDN telephony~\cite{jerichow-jsac98,isdn-mixes}. +Later low-latency designs used rendezvous points for hiding location +of mobile phones and low-power location +trackers~\cite{federrath-ih96,reed-protocols97}. Rendezvous for +anonymizing low-latency +Internet connections was suggested in early Onion Routing +work~\cite{or-ih96}, but the first published design was by Ian +Goldberg~\cite{ian-thesis}. His design differs from +ours in three ways. First, Goldberg suggests that Alice should manually +hunt down a current location of the service via Gnutella; our approach +makes lookup transparent to the user, as well as faster and more robust. +Second, in Tor the client and server negotiate session keys +with Diffie-Hellman, so plaintext is not exposed even at the rendezvous +point. Third, +our design minimizes the exposure from running the +service, to encourage volunteers to offer introduction and rendezvous +services. Tor's introduction points do not output any bytes to the +clients; the rendezvous points don't know the client or the server, +and can't read the data being transmitted. The indirection scheme is +also designed to include authentication/authorization---if Alice doesn't +include the right cookie with her request for service, Bob need not even +acknowledge his existence. + +\section{Other design decisions} +\label{sec:other-design} + +\subsection{Denial of service} +\label{subsec:dos} + +Providing Tor as a public service creates many opportunities for +denial-of-service attacks against the network. While +flow control and rate limiting (discussed in +Section~\ref{subsec:congestion}) prevent users from consuming more +bandwidth than routers are willing to provide, opportunities remain for +users to +consume more network resources than their fair share, or to render the +network unusable for others. + +First of all, there are several CPU-consuming denial-of-service +attacks wherein an attacker can force an OR to perform expensive +cryptographic operations. For example, an attacker can +%\emph{create} cell full of junk bytes can force an OR to perform an RSA +%decrypt. +%Similarly, an attacker can +fake the start of a TLS handshake, forcing the OR to carry out its +(comparatively expensive) half of the handshake at no real computational +cost to the attacker. + +We have not yet implemented any defenses for these attacks, but several +approaches are possible. First, ORs can +require clients to solve a puzzle~\cite{puzzles-tls} while beginning new +TLS handshakes or accepting \emph{create} cells. So long as these +tokens are easy to verify and computationally expensive to produce, this +approach limits the attack multiplier. Additionally, ORs can limit +the rate at which they accept \emph{create} cells and TLS connections, +so that +the computational work of processing them does not drown out the +symmetric cryptography operations that keep cells +flowing. This rate limiting could, however, allow an attacker +to slow down other users when they build new circuits. + +% What about link-to-link rate limiting? + +Adversaries can also attack the Tor network's hosts and network +links. Disrupting a single circuit or link breaks all streams passing +along that part of the circuit. Users similarly lose service +when a router crashes or its operator restarts it. The current +Tor design treats such attacks as intermittent network failures, and +depends on users and applications to respond or recover as appropriate. A +future design could use an end-to-end TCP-like acknowledgment protocol, +so no streams are lost unless the entry or exit point is +disrupted. This solution would require more buffering at the network +edges, however, and the performance and anonymity implications from this +extra complexity still require investigation. + +\subsection{Exit policies and abuse} +\label{subsec:exitpolicies} + +% originally, we planned to put the "users only know the hostname, +% not the IP, but exit policies are by IP" problem here too. Not +% worth putting in the submission, but worth thinking about putting +% in sometime somehow. -RD + +Exit abuse is a serious barrier to wide-scale Tor deployment. Anonymity +presents would-be vandals and abusers with an opportunity to hide +the origins of their activities. Attackers can harm the Tor network by +implicating exit servers for their abuse. Also, applications that commonly +use IP-based authentication (such as institutional mail or webservers) +can be fooled by the fact that anonymous connections appear to originate +at the exit OR. + +We stress that Tor does not enable any new class of abuse. Spammers +and other attackers already have access to thousands of misconfigured +systems worldwide, and the Tor network is far from the easiest way +to launch attacks. +%Indeed, because of its limited +%anonymity, Tor is probably not a good way to commit crimes. +But because the +onion routers can be mistaken for the originators of the abuse, +and the volunteers who run them may not want to deal with the hassle of +explaining anonymity networks to irate administrators, we must block or limit +abuse through the Tor network. + +To mitigate abuse issues, each onion router's \emph{exit policy} +describes to which external addresses and ports the router will +connect. On one end of the spectrum are \emph{open exit} +nodes that will connect anywhere. On the other end are \emph{middleman} +nodes that only relay traffic to other Tor nodes, and \emph{private exit} +nodes that only connect to a local host or network. A private +exit can allow a client to connect to a given host or +network more securely---an external adversary cannot eavesdrop traffic +between the private exit and the final destination, and so is less sure of +Alice's destination and activities. Most onion routers in the current +network function as +\emph{restricted exits} that permit connections to the world at large, +but prevent access to certain abuse-prone addresses and services such +as SMTP. +The OR might also be able to authenticate clients to +prevent exit abuse without harming anonymity~\cite{or-discex00}. + +%The abuse issues on closed (e.g. military) networks are different +%from the abuse on open networks like the Internet. While these IP-based +%access controls are still commonplace on the Internet, on closed networks, +%nearly all participants will be honest, and end-to-end authentication +%can be assumed for important traffic. + +Many administrators use port restrictions to support only a +limited set of services, such as HTTP, SSH, or AIM. +This is not a complete solution, of course, since abuse opportunities for these +protocols are still well known. + +We have not yet encountered any abuse in the deployed network, but if +we do we should consider using proxies to clean traffic for certain +protocols as it leaves the network. For example, much abusive HTTP +behavior (such as exploiting buffer overflows or well-known script +vulnerabilities) can be detected in a straightforward manner. +Similarly, one could run automatic spam filtering software (such as +SpamAssassin) on email exiting the OR network. + +ORs may also rewrite exiting traffic to append +headers or other information indicating that the traffic has passed +through an anonymity service. This approach is commonly used +by email-only anonymity systems. ORs can also +run on servers with hostnames like {\tt anonymous} to further +alert abuse targets to the nature of the anonymous traffic. + +A mixture of open and restricted exit nodes allows the most +flexibility for volunteers running servers. But while having many +middleman nodes provides a large and robust network, +having only a few exit nodes reduces the number of points +an adversary needs to monitor for traffic analysis, and places a +greater burden on the exit nodes. This tension can be seen in the +Java Anon Proxy +cascade model, wherein only one node in each cascade needs to handle +abuse complaints---but an adversary only needs to observe the entry +and exit of a cascade to perform traffic analysis on all that +cascade's users. The hydra model (many entries, few exits) presents a +different compromise: only a few exit nodes are needed, but an +adversary needs to work harder to watch all the clients; see +Section~\ref{sec:conclusion}. + +Finally, we note that exit abuse must not be dismissed as a peripheral +issue: when a system's public image suffers, it can reduce the number +and diversity of that system's users, and thereby reduce the anonymity +of the system itself. Like usability, public perception is a +security parameter. Sadly, preventing abuse of open exit nodes is an +unsolved problem, and will probably remain an arms race for the +foreseeable future. The abuse problems faced by Princeton's CoDeeN +project~\cite{darkside} give us a glimpse of likely issues. + +\subsection{Directory Servers} +\label{subsec:dirservers} + +First-generation Onion Routing designs~\cite{freedom2-arch,or-jsac98} used +in-band network status updates: each router flooded a signed statement +to its neighbors, which propagated it onward. But anonymizing networks +have different security goals than typical link-state routing protocols. +For example, delays (accidental or intentional) +that can cause different parts of the network to have different views +of link-state and topology are not only inconvenient: they give +attackers an opportunity to exploit differences in client knowledge. +We also worry about attacks to deceive a +client about the router membership list, topology, or current network +state. Such \emph{partitioning attacks} on client knowledge help an +adversary to efficiently deploy resources +against a target~\cite{minion-design}. + +Tor uses a small group of redundant, well-known onion routers to +track changes in network topology and node state, including keys and +exit policies. Each such \emph{directory server} acts as an HTTP +server, so clients can fetch current network state +and router lists, and so other ORs can upload +state information. Onion routers periodically publish signed +statements of their state to each directory server. The directory servers +combine this information with their own views of network liveness, +and generate a signed description (a \emph{directory}) of the entire +network state. Client software is +pre-loaded with a list of the directory servers and their keys, +to bootstrap each client's view of the network. +% XXX this means that clients will be forced to upgrade as the +% XXX dirservers change or get compromised. argue that this is ok. + +When a directory server receives a signed statement for an OR, it +checks whether the OR's identity key is recognized. Directory +servers do not advertise unrecognized ORs---if they did, +an adversary could take over the network by creating many +servers~\cite{sybil}. Instead, new nodes must be approved by the +directory +server administrator before they are included. Mechanisms for automated +node approval are an area of active research, and are discussed more +in Section~\ref{sec:maintaining-anonymity}. + +Of course, a variety of attacks remain. An adversary who controls +a directory server can track clients by providing them different +information---perhaps by listing only nodes under its control, or by +informing only certain clients about a given node. Even an external +adversary can exploit differences in client knowledge: clients who use +a node listed on one directory server but not the others are vulnerable. + +Thus these directory servers must be synchronized and redundant, so +that they can agree on a common directory. Clients should only trust +this directory if it is signed by a threshold of the directory +servers. + +The directory servers in Tor are modeled after those in +Mixminion~\cite{minion-design}, but our situation is easier. First, +we make the +simplifying assumption that all participants agree on the set of +directory servers. Second, while Mixminion needs to predict node +behavior, Tor only needs a threshold consensus of the current +state of the network. Third, we assume that we can fall back to the +human administrators to discover and resolve problems when a consensus +directory cannot be reached. Since there are relatively few directory +servers (currently 3, but we expect as many as 9 as the network scales), +we can afford operations like broadcast to simplify the consensus-building +protocol. + +To avoid attacks where a router connects to all the directory servers +but refuses to relay traffic from other routers, the directory servers +must also build circuits and use them to anonymously test router +reliability~\cite{mix-acc}. Unfortunately, this defense is not yet +designed or +implemented. + +Using directory servers is simpler and more flexible than flooding. +Flooding is expensive, and complicates the analysis when we +start experimenting with non-clique network topologies. Signed +directories can be cached by other +onion routers, +so directory servers are not a performance +bottleneck when we have many users, and do not aid traffic analysis by +forcing clients to announce their existence to any +central point. + +\section{Attacks and Defenses} +\label{sec:attacks} + +Below we summarize a variety of attacks, and discuss how well our +design withstands them.\\ + +\noindent{\large\bf Passive attacks}\\ +\emph{Observing user traffic patterns.} Observing a user's connection +will not reveal her destination or data, but it will +reveal traffic patterns (both sent and received). Profiling via user +connection patterns requires further processing, because multiple +application streams may be operating simultaneously or in series over +a single circuit. + +\emph{Observing user content.} While content at the user end is encrypted, +connections to responders may not be (indeed, the responding website +itself may be hostile). While filtering content is not a primary goal +of Onion Routing, Tor can directly use Privoxy and related +filtering services to anonymize application data streams. + +\emph{Option distinguishability.} We allow clients to choose +configuration options. For example, clients concerned about request +linkability should rotate circuits more often than those concerned +about traceability. Allowing choice may attract users with different +%There is economic incentive to attract users by +%allowing this choice; +needs; but clients who are +in the minority may lose more anonymity by appearing distinct than they +gain by optimizing their behavior~\cite{econymics}. + +\emph{End-to-end timing correlation.} Tor only minimally hides +such correlations. An attacker watching patterns of +traffic at the initiator and the responder will be +able to confirm the correspondence with high probability. The +greatest protection currently available against such confirmation is to hide +the connection between the onion proxy and the first Tor node, +by running the OP on the Tor node or behind a firewall. This approach +requires an observer to separate traffic originating at the onion +router from traffic passing through it: a global observer can do this, +but it might be beyond a limited observer's capabilities. + +\emph{End-to-end size correlation.} Simple packet counting +will also be effective in confirming +endpoints of a stream. However, even without padding, we may have some +limited protection: the leaky pipe topology means different numbers +of packets may enter one end of a circuit than exit at the other. + +\emph{Website fingerprinting.} All the effective passive +attacks above are traffic confirmation attacks, +which puts them outside our design goals. There is also +a passive traffic analysis attack that is potentially effective. +Rather than searching exit connections for timing and volume +correlations, the adversary may build up a database of +``fingerprints'' containing file sizes and access patterns for +targeted websites. He can later confirm a user's connection to a given +site simply by consulting the database. This attack has +been shown to be effective against SafeWeb~\cite{hintz-pet02}. +It may be less effective against Tor, since +streams are multiplexed within the same circuit, and +fingerprinting will be limited to +the granularity of cells (currently 512 bytes). Additional +defenses could include +larger cell sizes, padding schemes to group websites +into large sets, and link +padding or long-range dummies.\footnote{Note that this fingerprinting +attack should not be confused with the much more complicated latency +attacks of~\cite{back01}, which require a fingerprint of the latencies +of all circuits through the network, combined with those from the +network edges to the target user and the responder website.}\\ + +\noindent{\large\bf Active attacks}\\ +\emph{Compromise keys.} An attacker who learns the TLS session key can +see control cells and encrypted relay cells on every circuit on that +connection; learning a circuit +session key lets him unwrap one layer of the encryption. An attacker +who learns an OR's TLS private key can impersonate that OR for the TLS +key's lifetime, but he must +also learn the onion key to decrypt \emph{create} cells (and because of +perfect forward secrecy, he cannot hijack already established circuits +without also compromising their session keys). Periodic key rotation +limits the window of opportunity for these attacks. On the other hand, +an attacker who learns a node's identity key can replace that node +indefinitely by sending new forged descriptors to the directory servers. + +\emph{Iterated compromise.} A roving adversary who can +compromise ORs (by system intrusion, legal coercion, or extralegal +coercion) could march down the circuit compromising the +nodes until he reaches the end. Unless the adversary can complete +this attack within the lifetime of the circuit, however, the ORs +will have discarded the necessary information before the attack can +be completed. (Thanks to the perfect forward secrecy of session +keys, the attacker cannot force nodes to decrypt recorded +traffic once the circuits have been closed.) Additionally, building +circuits that cross jurisdictions can make legal coercion +harder---this phenomenon is commonly called ``jurisdictional +arbitrage.'' The Java Anon Proxy project recently experienced the +need for this approach, when +a German court forced them to add a backdoor to +their nodes~\cite{jap-backdoor}. + +\emph{Run a recipient.} An adversary running a webserver +trivially learns the timing patterns of users connecting to it, and +can introduce arbitrary patterns in its responses. +End-to-end attacks become easier: if the adversary can induce +users to connect to his webserver (perhaps by advertising +content targeted to those users), he now holds one end of their +connection. There is also a danger that application +protocols and associated programs can be induced to reveal information +about the initiator. Tor depends on Privoxy and similar protocol cleaners +to solve this latter problem. + +\emph{Run an onion proxy.} It is expected that end users will +nearly always run their own local onion proxy. However, in some +settings, it may be necessary for the proxy to run +remotely---typically, in institutions that want +to monitor the activity of those connecting to the proxy. +Compromising an onion proxy compromises all future connections +through it. + +\emph{DoS non-observed nodes.} An observer who can only watch some +of the Tor network can increase the value of this traffic +by attacking non-observed nodes to shut them down, reduce +their reliability, or persuade users that they are not trustworthy. +The best defense here is robustness. + +\emph{Run a hostile OR.} In addition to being a local observer, +an isolated hostile node can create circuits through itself, or alter +traffic patterns to affect traffic at other nodes. Nonetheless, a hostile +node must be immediately adjacent to both endpoints to compromise the +anonymity of a circuit. If an adversary can +run multiple ORs, and can persuade the directory servers +that those ORs are trustworthy and independent, then occasionally +some user will choose one of those ORs for the start and another +as the end of a circuit. If an adversary +controls $m>1$ of $N$ nodes, he can correlate at most +$\left(\frac{m}{N}\right)^2$ of the traffic---although an +adversary +could still attract a disproportionately large amount of traffic +by running an OR with a permissive exit policy, or by +degrading the reliability of other routers. + +\emph{Introduce timing into messages.} This is simply a stronger +version of passive timing attacks already discussed earlier. + +\emph{Tagging attacks.} A hostile node could ``tag'' a +cell by altering it. If the +stream were, for example, an unencrypted request to a Web site, +the garbled content coming out at the appropriate time would confirm +the association. However, integrity checks on cells prevent +this attack. + +\emph{Replace contents of unauthenticated protocols.} When +relaying an unauthenticated protocol like HTTP, a hostile exit node +can impersonate the target server. Clients +should prefer protocols with end-to-end authentication. + +\emph{Replay attacks.} Some anonymity protocols are vulnerable +to replay attacks. Tor is not; replaying one side of a handshake +will result in a different negotiated session key, and so the rest +of the recorded session can't be used. + +\emph{Smear attacks.} An attacker could use the Tor network for +socially disapproved acts, to bring the +network into disrepute and get its operators to shut it down. +Exit policies reduce the possibilities for abuse, but +ultimately the network requires volunteers who can tolerate +some political heat. + +\emph{Distribute hostile code.} An attacker could trick users +into running subverted Tor software that did not, in fact, anonymize +their connections---or worse, could trick ORs into running weakened +software that provided users with less anonymity. We address this +problem (but do not solve it completely) by signing all Tor releases +with an official public key, and including an entry in the directory +that lists which versions are currently believed to be secure. To +prevent an attacker from subverting the official release itself +(through threats, bribery, or insider attacks), we provide all +releases in source code form, encourage source audits, and +frequently warn our users never to trust any software (even from +us) that comes without source.\\ + +\noindent{\large\bf Directory attacks}\\ +\emph{Destroy directory servers.} If a few directory +servers disappear, the others still decide on a valid +directory. So long as any directory servers remain in operation, +they will still broadcast their views of the network and generate a +consensus directory. (If more than half are destroyed, this +directory will not, however, have enough signatures for clients to +use it automatically; human intervention will be necessary for +clients to decide whether to trust the resulting directory.) + +\emph{Subvert a directory server.} By taking over a directory server, +an attacker can partially influence the final directory. Since ORs +are included or excluded by majority vote, the corrupt directory can +at worst cast a tie-breaking vote to decide whether to include +marginal ORs. It remains to be seen how often such marginal cases +occur in practice. + +\emph{Subvert a majority of directory servers.} An adversary who controls +more than half the directory servers can include as many compromised +ORs in the final directory as he wishes. We must ensure that directory +server operators are independent and attack-resistant. + +\emph{Encourage directory server dissent.} The directory +agreement protocol assumes that directory server operators agree on +the set of directory servers. An adversary who can persuade some +of the directory server operators to distrust one another could +split the quorum into mutually hostile camps, thus partitioning +users based on which directory they use. Tor does not address +this attack. + +\emph{Trick the directory servers into listing a hostile OR.} +Our threat model explicitly assumes directory server operators will +be able to filter out most hostile ORs. +% If this is not true, an +% attacker can flood the directory with compromised servers. + +\emph{Convince the directories that a malfunctioning OR is +working.} In the current Tor implementation, directory servers +assume that an OR is running correctly if they can start a TLS +connection to it. A hostile OR could easily subvert this test by +accepting TLS connections from ORs but ignoring all cells. Directory +servers must actively test ORs by building circuits and streams as +appropriate. The tradeoffs of a similar approach are discussed +in~\cite{mix-acc}.\\ + +\noindent{\large\bf Attacks against rendezvous points}\\ +\emph{Make many introduction requests.} An attacker could +try to deny Bob service by flooding his introduction points with +requests. Because the introduction points can block requests that +lack authorization tokens, however, Bob can restrict the volume of +requests he receives, or require a certain amount of computation for +every request he receives. + +\emph{Attack an introduction point.} An attacker could +disrupt a location-hidden service by disabling its introduction +points. But because a service's identity is attached to its public +key, the service can simply re-advertise +itself at a different introduction point. Advertisements can also be +done secretly so that only high-priority clients know the address of +Bob's introduction points or so that different clients know of different +introduction points. This forces the attacker to disable all possible +introduction points. + +\emph{Compromise an introduction point.} An attacker who controls +Bob's introduction point can flood Bob with +introduction requests, or prevent valid introduction requests from +reaching him. Bob can notice a flood, and close the circuit. To notice +blocking of valid requests, however, he should periodically test the +introduction point by sending rendezvous requests and making +sure he receives them. + +\emph{Compromise a rendezvous point.} A rendezvous +point is no more sensitive than any other OR on +a circuit, since all data passing through the rendezvous is encrypted +with a session key shared by Alice and Bob. + +\section{Early experiences: Tor in the Wild} +\label{sec:in-the-wild} + +As of mid-May 2004, the Tor network consists of 32 nodes +(24 in the US, 8 in Europe), and more are joining each week as the code +matures. (For comparison, the current remailer network +has about 40 nodes.) % We haven't asked PlanetLab to provide +%Tor nodes, since their AUP wouldn't allow exit nodes (see +%also~\cite{darkside}) and because we aim to build a long-term community of +%node operators and developers.} +Each node has at least a 768Kb/768Kb connection, and +many have 10Mb. The number of users varies (and of course, it's hard to +tell for sure), but we sometimes have several hundred users---administrators at +several companies have begun sending their entire departments' web +traffic through Tor, to block other divisions of +their company from reading their traffic. Tor users have reported using +the network for web browsing, FTP, IRC, AIM, Kazaa, SSH, and +recipient-anonymous email via rendezvous points. One user has anonymously +set up a Wiki as a hidden service, where other users anonymously publish +the addresses of their hidden services. + +Each Tor node currently processes roughly 800,000 relay +cells (a bit under half a gigabyte) per week. On average, about 80\% +of each 498-byte payload is full for cells going back to the client, +whereas about 40\% is full for cells coming from the client. (The difference +arises because most of the network's traffic is web browsing.) Interactive +traffic like SSH brings down the average a lot---once we have more +experience, and assuming we can resolve the anonymity issues, we may +partition traffic into two relay cell sizes: one to handle +bulk traffic and one for interactive traffic. + +Based in part on our restrictive default exit policy (we +reject SMTP requests) and our low profile, we have had no abuse +issues since the network was deployed in October +2003. Our slow growth rate gives us time to add features, +resolve bugs, and get a feel for what users actually want from an +anonymity system. Even though having more users would bolster our +anonymity sets, we are not eager to attract the Kazaa or warez +communities---we feel that we must build a reputation for privacy, human +rights, research, and other socially laudable activities. + +As for performance, profiling shows that Tor spends almost +all its CPU time in AES, which is fast. Current latency is attributable +to two factors. First, network latency is critical: we are +intentionally bouncing traffic around the world several times. Second, +our end-to-end congestion control algorithm focuses on protecting +volunteer servers from accidental DoS rather than on optimizing +performance. % Right now the first $500 \times 500\mbox{B}=250\mbox{KB}$ +%of the stream arrives +%quickly, and after that throughput depends on the rate that \emph{relay +%sendme} acknowledgments arrive. +To quantify these effects, we did some informal tests using a network of 4 +nodes on the same machine (a heavily loaded 1GHz Athlon). We downloaded a 60 +megabyte file from {\tt debian.org} every 30 minutes for 54 hours (108 sample +points). It arrived in about 300 seconds on average, compared to 210s for a +direct download. We ran a similar test on the production Tor network, +fetching the front page of {\tt cnn.com} (55 kilobytes): +% every 20 seconds for 8952 data points +while a direct +download consistently took about 0.3s, the performance through Tor varied. +Some downloads were as fast as 0.4s, with a median at 2.8s, and +90\% finishing within 5.3s. It seems that as the network expands, the chance +of building a slow circuit (one that includes a slow or heavily loaded node +or link) is increasing. On the other hand, as our users remain satisfied +with this increased latency, we can address our performance incrementally as we +proceed with development. %\footnote{For example, we have just begun pushing +%a pipelining patch to the production network that seems to decrease +%latency for medium-to-large files; we will present revised benchmarks +%as they become available.} + +%With the current network's topology and load, users can typically get 1-2 +%megabits sustained transfer rate, which is good enough for now. +%Indeed, the Tor +%design aims foremost to provide a security research platform; performance +%only needs to be sufficient to retain users~\cite{econymics,back01}. +%We can tweak the congestion control +%parameters to provide faster throughput at the cost of +%larger buffers at each node; adding the heuristics mentioned in +%Section~\ref{subsec:rate-limit} to favor low-volume +%streams may also help. More research remains to find the +%right balance. +% We should say _HOW MUCH_ latency there is in these cases. -NM + +%performs badly on lossy networks. may need airhook or something else as +%transport alternative? + +Although Tor's clique topology and full-visibility directories present +scaling problems, we still expect the network to support a few hundred +nodes and maybe 10,000 users before we're forced to become +more distributed. With luck, the experience we gain running the current +topology will help us choose among alternatives when the time comes. + +\section{Open Questions in Low-latency Anonymity} +\label{sec:maintaining-anonymity} + +In addition to the non-goals in +Section~\ref{subsec:non-goals}, many questions must be solved +before we can be confident of Tor's security. + +Many of these open issues are questions of balance. For example, +how often should users rotate to fresh circuits? Frequent rotation +is inefficient, expensive, and may lead to intersection attacks and +predecessor attacks~\cite{wright03}, but infrequent rotation makes the +user's traffic linkable. Besides opening fresh circuits, clients can +also exit from the middle of the circuit, +or truncate and re-extend the circuit. More analysis is +needed to determine the proper tradeoff. + +%% Duplicated by 'Better directory distribution' in section 9. +% +%A similar question surrounds timing of directory operations: how often +%should directories be updated? Clients that update infrequently receive +%an inaccurate picture of the network, but frequent updates can overload +%the directory servers. More generally, we must find more +%decentralized yet practical ways to distribute up-to-date snapshots of +%network status without introducing new attacks. + +How should we choose path lengths? If Alice always uses two hops, +then both ORs can be certain that by colluding they will learn about +Alice and Bob. In our current approach, Alice always chooses at least +three nodes unrelated to herself and her destination. +%% This point is subtle, but not IMO necessary. Anybody who thinks +%% about it will see that it's implied by the above sentence; anybody +%% who doesn't think about it is safe in his ignorance. +% +%Thus normally she chooses +%three nodes, but if she is running an OR and her destination is on an OR, +%she uses five. +Should Alice choose a random path length (e.g.~from a geometric +distribution) to foil an attacker who +uses timing to learn that he is the fifth hop and thus concludes that +both Alice and the responder are running ORs? + +Throughout this paper, we have assumed that end-to-end traffic +confirmation will immediately and automatically defeat a low-latency +anonymity system. Even high-latency anonymity systems can be +vulnerable to end-to-end traffic confirmation, if the traffic volumes +are high enough, and if users' habits are sufficiently +distinct~\cite{statistical-disclosure,limits-open}. Can anything be +done to +make low-latency systems resist these attacks as well as high-latency +systems? Tor already makes some effort to conceal the starts and ends of +streams by wrapping long-range control commands in identical-looking +relay cells. Link padding could frustrate passive observers who count +packets; long-range padding could work against observers who own the +first hop in a circuit. But more research remains to find an efficient +and practical approach. Volunteers prefer not to run constant-bandwidth +padding; but no convincing traffic shaping approach has been +specified. Recent work on long-range padding~\cite{defensive-dropping} +shows promise. One could also try to reduce correlation in packet timing +by batching and re-ordering packets, but it is unclear whether this could +improve anonymity without introducing so much latency as to render the +network unusable. + +A cascade topology may better defend against traffic confirmation by +aggregating users, and making padding and +mixing more affordable. Does the hydra topology (many input nodes, +few output nodes) work better against some adversaries? Are we going +to get a hydra anyway because most nodes will be middleman nodes? + +Common wisdom suggests that Alice should run her own OR for best +anonymity, because traffic coming from her node could plausibly have +come from elsewhere. How much mixing does this approach need? Is it +immediately beneficial because of real-world adversaries that can't +observe Alice's router, but can run routers of their own? + +To scale to many users, and to prevent an attacker from observing the +whole network, it may be necessary +to support far more servers than Tor currently anticipates. +This introduces several issues. First, if approval by a central set +of directory servers is no longer feasible, what mechanism should be used +to prevent adversaries from signing up many colluding servers? Second, +if clients can no longer have a complete picture of the network, +how can they perform discovery while preventing attackers from +manipulating or exploiting gaps in their knowledge? Third, if there +are too many servers for every server to constantly communicate with +every other, which non-clique topology should the network use? +(Restricted-route topologies promise comparable anonymity with better +scalability~\cite{danezis-pets03}, but whatever topology we choose, we +need some way to keep attackers from manipulating their position within +it~\cite{casc-rep}.) Fourth, if no central authority is tracking +server reliability, how do we stop unreliable servers from making +the network unusable? Fifth, do clients receive so much anonymity +from running their own ORs that we should expect them all to do +so~\cite{econymics}, or do we need another incentive structure to +motivate them? Tarzan and MorphMix present possible solutions. + +% advogato, captcha + +When a Tor node goes down, all its circuits (and thus streams) must break. +Will users abandon the system because of this brittleness? How well +does the method in Section~\ref{subsec:dos} allow streams to survive +node failure? If affected users rebuild circuits immediately, how much +anonymity is lost? It seems the problem is even worse in a peer-to-peer +environment---such systems don't yet provide an incentive for peers to +stay connected when they're done retrieving content, so we would expect +a higher churn rate. + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +\section{Future Directions} +\label{sec:conclusion} + +Tor brings together many innovations into a unified deployable system. The +next immediate steps include: + +\emph{Scalability:} Tor's emphasis on deployability and design simplicity +has led us to adopt a clique topology, semi-centralized +directories, and a full-network-visibility model for client +knowledge. These properties will not scale past a few hundred servers. +Section~\ref{sec:maintaining-anonymity} describes some promising +approaches, but more deployment experience will be helpful in learning +the relative importance of these bottlenecks. + +\emph{Bandwidth classes:} This paper assumes that all ORs have +good bandwidth and latency. We should instead adopt the MorphMix model, +where nodes advertise their bandwidth level (DSL, T1, T3), and +Alice avoids bottlenecks by choosing nodes that match or +exceed her bandwidth. In this way DSL users can usefully join the Tor +network. + +\emph{Incentives:} Volunteers who run nodes are rewarded with publicity +and possibly better anonymity~\cite{econymics}. More nodes means increased +scalability, and more users can mean more anonymity. We need to continue +examining the incentive structures for participating in Tor. Further, +we need to explore more approaches to limiting abuse, and understand +why most people don't bother using privacy systems. + +\emph{Cover traffic:} Currently Tor omits cover traffic---its costs +in performance and bandwidth are clear but its security benefits are +not well understood. We must pursue more research on link-level cover +traffic and long-range cover traffic to determine whether some simple padding +method offers provable protection against our chosen adversary. + +%%\emph{Offer two relay cell sizes:} Traffic on the Internet tends to be +%%large for bulk transfers and small for interactive traffic. One cell +%%size cannot be optimal for both types of traffic. +% This should go in the spec and todo, but not the paper yet. -RD + +\emph{Caching at exit nodes:} Perhaps each exit node should run a +caching web proxy~\cite{shsm03}, to improve anonymity for cached pages +(Alice's request never +leaves the Tor network), to improve speed, and to reduce bandwidth cost. +On the other hand, forward security is weakened because caches +constitute a record of retrieved files. We must find the right +balance between usability and security. + +\emph{Better directory distribution:} +Clients currently download a description of +the entire network every 15 minutes. As the state grows larger +and clients more numerous, we may need a solution in which +clients receive incremental updates to directory state. +More generally, we must find more +scalable yet practical ways to distribute up-to-date snapshots of +network status without introducing new attacks. + +\emph{Further specification review:} Our public +byte-level specification~\cite{tor-spec} needs +external review. We hope that as Tor +is deployed, more people will examine its +specification. + +\emph{Multisystem interoperability:} We are currently working with the +designer of MorphMix to unify the specification and implementation of +the common elements of our two systems. So far, this seems +to be relatively straightforward. Interoperability will allow testing +and direct comparison of the two designs for trust and scalability. + +\emph{Wider-scale deployment:} The original goal of Tor was to +gain experience in deploying an anonymizing overlay network, and +learn from having actual users. We are now at a point in design +and development where we can start deploying a wider network. Once +we have many actual users, we will doubtlessly be better +able to evaluate some of our design decisions, including our +robustness/latency tradeoffs, our performance tradeoffs (including +cell size), our abuse-prevention mechanisms, and +our overall usability. + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +%% commented out for anonymous submission +\section*{Acknowledgments} + We thank Peter Palfrader, Geoff Goodell, Adam Shostack, Joseph Sokol-Margolis, + John Bashinski, and Zack Brown + for editing and comments; + Matej Pfajfar, Andrei Serjantov, Marc Rennhard for design discussions; + Bram Cohen for congestion control discussions; + Adam Back for suggesting telescoping circuits; and + Cathy Meadows for formal analysis of the \emph{extend} protocol. + This work has been supported by ONR and DARPA. + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +\bibliographystyle{latex8} +\bibliography{tor-design} + +\end{document} + +% Style guide: +% U.S. spelling +% avoid contractions (it's, can't, etc.) +% prefer ``for example'' or ``such as'' to e.g. +% prefer ``that is'' to i.e. +% 'mix', 'mixes' (as noun) +% 'mix-net' +% 'mix', 'mixing' (as verb) +% 'middleman' [Not with a hyphen; the hyphen has been optional +% since Middle English.] +% 'nymserver' +% 'Cypherpunk', 'Cypherpunks', 'Cypherpunk remailer' +% 'Onion Routing design', 'onion router' [note capitalization] +% 'SOCKS' +% Try not to use \cite as a noun. +% 'Authorizating' sounds great, but it isn't a word. +% 'First, second, third', not 'Firstly, secondly, thirdly'. +% 'circuit', not 'channel' +% Typography: no space on either side of an em dash---ever. +% Hyphens are for multi-part words; en dashs imply movement or +% opposition (The Alice--Bob connection); and em dashes are +% for punctuation---like that. +% A relay cell; a control cell; a \emph{create} cell; a +% \emph{relay truncated} cell. Never ``a \emph{relay truncated}.'' +% +% 'Substitute ``Damn'' every time you're inclined to write ``very;'' your +% editor will delete it and the writing will be just as it should be.' +% -- Mark Twain diff --git a/doc/design-paper/usenix.sty b/doc/design-paper/usenix.sty new file mode 100644 index 0000000000..4442f11574 --- /dev/null +++ b/doc/design-paper/usenix.sty @@ -0,0 +1,98 @@ +% usenix-2e.sty - to be used with latex2e (the new one) for USENIX. +% To use this style file, do this: +% +% \documentclass[twocolumn]{article} +% \usepackage{usenix-2e} +% and put {\rm ....} around the author names. +% +% $Id$ +% +% The following definitions are modifications of standard article.sty +% definitions, arranged to do a better job of matching the USENIX +% guidelines. +% It will automatically select two-column mode and the Times-Roman +% font. + +% +% USENIX papers are two-column. +% Times-Roman font is nice if you can get it (requires NFSS, +% which is in latex2e. + +\if@twocolumn\else\input twocolumn.sty\fi +\usepackage{times} + +% +% USENIX wants margins of: 7/8" side, 1" bottom, and 3/4" top. +% 0.25" gutter between columns. +% Gives active areas of 6.75" x 9.25" +% +\setlength{\textheight}{9.0in} +\setlength{\columnsep}{0.25in} +%%\setlength{\textwidth}{6.75in} +\setlength{\textwidth}{7.00in} +%\setlength{\footheight}{0.0in} +\setlength{\topmargin}{-0.25in} +\setlength{\headheight}{0.0in} +\setlength{\headsep}{0.0in} +\setlength{\evensidemargin}{-0.125in} +\setlength{\oddsidemargin}{-0.125in} + +% +% Usenix wants no page numbers for submitted papers, so that they can +% number them themselves. +% +\pagestyle{empty} + +% +% Usenix titles are in 14-point bold type, with no date, and with no +% change in the empty page headers. The whol author section is 12 point +% italic--- you must use {\rm } around the actual author names to get +% them in roman. +% +\def\maketitle{\par + \begingroup + \renewcommand\thefootnote{\fnsymbol{footnote}}% + \def\@makefnmark{\hbox to\z@{$\m@th^{\@thefnmark}$\hss}}% + \long\def\@makefntext##1{\parindent 1em\noindent + \hbox to1.8em{\hss$\m@th^{\@thefnmark}$}##1}% + \if@twocolumn + \twocolumn[\@maketitle]% + \else \newpage + \global\@topnum\z@ + \@maketitle \fi\@thanks + \endgroup + \setcounter{footnote}{0}% + \let\maketitle\relax + \let\@maketitle\relax + \gdef\@thanks{}\gdef\@author{}\gdef\@title{}\let\thanks\relax} + +\def\@maketitle{\newpage + \vbox to 2.5in{ + \vspace*{\fill} + \vskip 2em + \begin{center}% + {\Large\bf \@title \par}% + \vskip 0.375in minus 0.300in + {\large\it + \lineskip .5em + \begin{tabular}[t]{c}\@author + \end{tabular}\par}% + \end{center}% + \par + \vspace*{\fill} +% \vskip 1.5em + } +} + +% +% The abstract is preceded by a 12-pt bold centered heading +\def\abstract{\begin{center}% +{\large\bf \abstractname\vspace{-.5em}\vspace{\z@}}% +\end{center}} +\def\endabstract{} + +% +% Main section titles are 12-pt bold. Others can be same or smaller. +% +\def\section{\@startsection {section}{1}{\z@}{-3.5ex plus-1ex minus + -.2ex}{2.3ex plus.2ex}{\reset@font\large\bf}} |
