Website Fingerprinting Attack on SSH with Random Forests Classifier

DOI

10.2991/icence-16.2016.148How to use a DOI?

Keywords

anonymity network website fingerprinting traffic analysis random forests

Abstract

In this paper, we implement a special websites fingerprinting attack based on SSH anonymous communication system with random decision forests classifier. When users access to the Internet through anonymous communication network, website fingerprinting attack can listen in the client passively to determine the source address to which user access, so as to achieve the goal of regulation and monitoring anonymous communication system. However, there are plenty of differences between our work and the previous research. We pay more attention to outgoing traffic which is sent by the servers to the client and achieving a well performance by extracting our own features with some specific strategies. According to the experiments, we have proven that the random decision forests classifier has better performance than other classifiers in the field of outgoing traffic.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yong-Jun Wei
AU  - Su-Juan Qin
PY  - 2016/09
DA  - 2016/09
TI  - Website Fingerprinting Attack on SSH with Random Forests Classifier
BT  - Proceedings of the 2nd International Conference on Electronics, Network and Computer Engineering (ICENCE 2016)
PB  - Atlantis Press
SP  - 803
EP  - 808
SN  - 2352-538X
UR  - https://doi.org/10.2991/icence-16.2016.148
DO  - 10.2991/icence-16.2016.148
ID  - Wei2016/09
ER  -