Website Fingerprinting Attack on SSH with Random Forests Classifier
Yongjun Wei, Su‐Juan Qin · 2016
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.