Var-CNN: A Data-Efficient Website Fingerprinting Attack Based on Deep Learning

TL;DR

Var-CNN is a deep learning-based website fingerprinting attack that significantly improves accuracy and reduces data requirements, especially in low-data scenarios, by leveraging novel packet sequence classification insights.

Contribution

It introduces Var-CNN, a novel deep learning approach that outperforms existing methods in accuracy and data efficiency for website fingerprinting attacks.

Findings

Over 1% higher true positive rate in large data settings

4x lower false positive rate compared to state-of-the-art

Significant improvements in low-data scenarios with reduced false positives

Abstract

In recent years, there have been several works that use website fingerprinting techniques to enable a local adversary to determine which website a Tor user visits. While the current state-of-the-art attack, which uses deep learning, outperforms prior art with medium to large amounts of data, it attains marginal to no accuracy improvements when both use small amounts of training data. In this work, we propose Var-CNN, a website fingerprinting attack that leverages deep learning techniques along with novel insights specific to packet sequence classification. In open-world settings with large amounts of data, Var-CNN attains over $1\%$ higher true positive rate (TPR) than state-of-the-art attacks while achieving $4\times$ lower false positive rate (FPR). Var-CNN's improvements are especially notable in low-data scenarios, where it reduces the FPR of prior art by $3.12\%$ while increasing the TPR by $13\%$. Overall, insights used to develop Var-CNN can be applied to future deep learning based attacks, and substantially reduce the amount of training data needed to perform a successful website fingerprinting attack. This shortens the time needed for data collection and lowers the likelihood of having data staleness issues.