k-fingerprinting: A Robust Scalable Website Fingerprinting Technique

By Jamie Hayes, George Danezis. USENIX Security Symposium, 2015

493 citations recorded by the source corpus.

Website fingerprinting enables an attacker to infer which web page a client is browsing through encrypted or anonymized network connections. We present a new website fingerprinting technique based on random decision forests and evaluate performance over standard web pages as well as Tor hidden services, on a larger scale than previous works. Our technique, k-fingerprinting, performs better than current state-of-the-art attacks even against website fingerprinting defenses, and we show that it is possible to launch a website fingerprinting attack in the face of a large amount of noisy data. We can correctly determine which of 30 monitored hidden services a client is visiting with 85% true positive rate (TPR), a false positive rate (FPR) as low as 0.02%, from a world size of 100,000 unmonitored web pages. We further show that error rates vary widely between web resources, and thus some patterns of use will be predictably more vulnerable to attack than others.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems

View Paper: https://www.semanticscholar.org/paper/b10c4f0ccade4e584415f407f5a9c115a607f9e0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification (2022, methodology): “We compare ET-BERT with various state-of-the-art (SOTA) methods, including (1) fingerprint construction method: FlowPrint [37]; (2) statistical featuremethods: AppScanner [36], CUMUL [27], BIND [1] and k-fingerprinting (K-fp) [12]; (3) deep learningmethods: Deep Fingerprinting (DF) [35], FS-Net [22]”
Automated Website Fingerprinting through Deep Learning (2017, unknown): “Proposed approaches have been shown to achieve a classiﬁcation accuracy of 91 - 96% correctly recognized websites [15], [25], [30] in a set of 100 websites with about as many traces per website.”