Neural-FacTOR: Neural Representation Learning for Website Fingerprinting Attack over TOR Anonymity

TL;DR

This paper introduces a neural network-based website fingerprinting attack on the TOR network, using CNN with dilation and causal convolution to improve accuracy and robustness over existing methods.

Contribution

It proposes a novel CNN-based model with dilation and causal convolution for website fingerprinting on TOR, outperforming prior approaches.

Findings

Achieved 12.21% higher accuracy than state-of-the-art methods.

Demonstrated robustness and effectiveness on three public datasets.

Enhanced perception field and sequence capturing in CNN model.

Abstract

TOR (The Onion Router) network is a widely used open source anonymous communication tool, the abuse of TOR makes it difficult to monitor the proliferation of online crimes such as to access criminal websites. Most existing approches for TOR network de-anonymization heavily rely on manually extracted features resulting in time consuming and poor performance. To tackle the shortcomings, this paper proposes a neural representation learning approach to recognize website fingerprint based on classification algorithm. We constructed a new website fingerprinting attack model based on convolutional neural network (CNN) with dilation and causal convolution, which can improve the perception field of CNN as well as capture the sequential characteristic of input data. Experiments on three mainstream public datasets show that the proposed model is robust and effective for the website fingerprint classification and improves the accuracy by 12.21% compared with the state-of-the-art methods.