Website fingerprinting: attacking popular privacy enhancing technologies with the multinomial naïve-bayes classifier

By Dominik Herrmann, Rolf Wendolsky, Hannes Federrath. 2009

492 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

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

In Computer Networks and Communications

In Signal Processing

Citations in the corpus

A Critical Evaluation of Website Fingerprinting Attacks (2014, unknown): “Website fingerprinting; Tor; privacy”
MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples (2019, background): “nd adversarial examples. Other than membership inference attacks, many other attacks rely on machine learning classifiers, e.g.,attribute inference attacks [11, 17, 28], website fingerprinting attacks[7, 22, 29, 46, 67], side-channel attacks [73], location attacks [5, 45, 52, 72], and author identif”
Circuit Fingerprinting Attacks: Passive Deanonymization of Tor Hidden Services (2015, methodology): “[20] were the first to test this attack against Tor using a multinomial Naive Bayes classifier, which only achieved 3% success rate since it relied on packet sizes which are fixed in Tor.”
Deep Fingerprinting: Undermining Website Fingerprinting Defenses with Deep Learning (2018, background): “The closed-world assumption was criticized for being unrealistic [13, 24, 15], as the world of sites that can be potentially visited is so large that not even the most powerful adversaries have the resources to collect data”
Improved website fingerprinting on Tor (2013, methodology): “[6] in 2009 described an improved method that gave a higher accuracy than Liberatore and Levine under comparable conditions.”
Website Fingerprinting at Internet Scale (2016, methodology): “[11] were the first to apply website fingerprinting to the anonymization networks JAP [2] and Tor [8] as well as on OpenSSH, OpenVPN, Stunnel, and Cisco IPsec-VPN.”
Mobile Encrypted Traffic Classification Using Deep Learning: Experimental Evaluation, Lessons Learned, and Challenges (2019, methodology): “[31] and [32] are also employed by Alan and Kaur [30] to check out whether Android apps can be identified from their launch-time traffic using only TCP/IP header information.”
Website fingerprinting in onion routing based anonymization networks (2011, methodology): “[11] in order to compare our results to previous best achieved results.”
k-fingerprinting: A Robust Scalable Website Fingerprinting Technique (2015, methodology): “As a result, many works have shown that website fingerprinting attacks are possible even when a client is browsing with encryption or using an anonymity tool such as Tor [7, 16, 17, 21, 23, 27, 32, 36, 38, 39].”
Touching from a distance: website fingerprinting attacks and defenses (2012, methodology): “, proposed a fingerprinting attack based on a Multinomial Naive-Bayes classifier [10], which, in our experiments is able to identify which web page a victim visited (out of a set of 100 possible pages) with a success rate of less than 5%.”
A Systematic Approach to Developing and Evaluating Website Fingerprinting Defenses (2014, background): “Therefore, the poor performance of most early WF attacks [6, 9, 10] may be attributed to the fact that they explicitly discard packet length frequencies.”
Robust Smartphone App Identification via Encrypted Network Traffic Analysis (2017, methodology): “Subsequently, Herman et al. [17] outperformed Liberatore et al. by presenting a method that relies on common text mining techniques to the normalized frequency distribution of observable IP packet sizes.”