Collected research
Touching from a Distance: Website Fingerprinting Attacks and Defenses
Shows application-level traffic-analysis defences fail: an SVM using Damerau-Levenshtein distance over packet-direction traces guessed which of 100 pages a Tor or SSH user loaded 83-92% of the time, defeating HTTPOS, randomised pipelining and traffic morphing. Hidden Markov models extend this to whole-site identification above 90% accuracy, and a provable BUFLO variant is proposed.
Record
- Researcher
- Xiang Cai, Xin Cheng Zhang, Brijesh Joshi and Rob Johnson
- Published by
- freehaven.net
- Format
- Whitepaper
- Topic
- Other
In the archive
Tags
This page is the archive's own catalogue record. The research is the work of Xiang Cai, Xin Cheng Zhang, Brijesh Joshi and Rob Johnson, first published at the original source. Preserved copies are kept so the citation survives its host; this one was last captured on .