SiamHAN: IPv6 Address Correlation Attacks on TLS Encrypted Traffic via Siamese Heterogeneous Graph Attention Network

April 20, 2022 · Entered Twilight · 🏛 USENIX Security Symposium

Repo contents: README.md, data, dataloader.py, images, inference_discovery.py, inference_tracking.py, models, pre_trained, train.py

Authors Tianyu Cui, Gaopeng Gou, Gang Xiong, Zhen Li, Mingxin Cui, Chang Liu arXiv ID 2204.09465 Category cs.CR: Cryptography & Security Cross-listed cs.AI, cs.NI Citations 20 Venue USENIX Security Symposium Repository https://github.com/CuiTianyu961030/SiamHAN ⭐ 18 Last Checked 1 month ago

Abstract

Unlike IPv4 addresses, which are typically masked by a NAT, IPv6 addresses could easily be correlated with user activity, endangering their privacy. Mitigations to address this privacy concern have been deployed, making existing approaches for address-to-user correlation unreliable. This work demonstrates that an adversary could still correlate IPv6 addresses with users accurately, even with these protection mechanisms. To do this, we propose an IPv6 address correlation model - SiamHAN. The model uses a Siamese Heterogeneous Graph Attention Network to measure whether two IPv6 client addresses belong to the same user even if the user's traffic is protected by TLS encryption. Using a large real-world dataset, we show that, for the tasks of tracking target users and discovering unique users, the state-of-the-art techniques could achieve only 85% and 60% accuracy, respectively. However, SiamHAN exhibits 99% and 88% accuracy.