WFCAT: Augmenting Website Fingerprinting with Channel-wise Attention on Timing Features

TL;DR

This paper introduces WFCAT, a CNN-based attack leveraging channel-wise attention on timing features, notably the IAT histogram, to significantly improve website fingerprinting accuracy against modern defenses.

Contribution

It proposes a novel timing feature representation and a CNN architecture with multi-scale kernels and channel-wise attention, enhancing attack robustness against defended traffic.

Findings

WFCAT achieves over 59% accuracy against Surakav defense.

It outperforms existing attacks by over 28% and 48% against RF and Tik-Tok defenses.

The approach effectively captures multi-scale timing features for improved classification.

Abstract

Website Fingerprinting (WF) aims to deanonymize users on the Tor network by analyzing encrypted network traffic. Recent deep-learning-based attacks show high accuracy on undefended traces. However, they struggle against modern defenses that use tactics like injecting dummy packets and delaying real packets, which significantly degrade classification performance. Our analysis reveals that current attacks inadequately leverage the timing information inherent in traffic traces, which persists as a source of leakage even under robust defenses. Addressing this shortfall, we introduce a novel feature representation named the Inter-Arrival Time (IAT) histogram, which quantifies the frequencies of packet inter-arrival times across predetermined time slots. Complementing this feature, we propose a new CNN-based attack, WFCAT, enhanced with two innovative architectural blocks designed to optimally extract and utilize timing information. Our approach uses kernels of varying sizes to capture multi-scale features, which are then integrated using a weighted sum across all feature channels to enhance the model's efficacy in identifying temporal patterns. Our experiments validate that WFCAT substantially outperforms existing methods on defended traces in both closed- and open-world scenarios. Notably, WFCAT achieves over 59% accuracy against Surakav, a recently developed robust defense, marking an improvement of over 28% and 48% against the state-of-the-art attacks RF and Tik-Tok, respectively, in the closed-world scenario.