A Critical Evaluation of Website Fingerprinting Attacks

By Marc Juárez, Sadia Afroz, Gunes Acar, Claudia Díaz, Rachel Greenstadt. Conference on Computer and Communications Security, 2014

366 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/7efcf9da1cc1093a08771e3467629bc7092f3abf

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 Information Systems

Citations in the corpus

Circuit Fingerprinting Attacks: Passive Deanonymization of Tor Hidden Services (2015, background): “…can correctly determine which of the 50 monitored pages the client is visiting with 88% true positive rate and false positive rate as low as 2.9%, and correctly deanonymize 50 monitored hidden service servers with true positive rate of 88% and false positive rate of 7.8% in an open world setting.”
k-fingerprinting: A Robust Scalable Website Fingerprinting Technique (2015, background): “Website fingerprinting research has been criticized for not being applicable to real-world scenarios [17, 29].”
ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification (2022, background): “Generalizability: The variability of encrypted traffic due to changes in the content of Internet services [13] over time will challenge the ability of our approach with fixed patterns leaned from fixed data and keeping unchanged over time.”
Deep Fingerprinting: Undermining Website Fingerprinting Defenses with Deep Learning (2018, methodology): “Both Juarez et al. [19] and Wang and Goldberg [40] show that after 10-14 days, the accuracy of WF attacks goes down significantly.”
Characterization of Tor Traffic using Time based Features (2017, background): “In (Juarez et al., 2014), the authors exploit the user’s browsing behaviour, along with location data and the version of the browser to execute a website fingerprinting attack.”
MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples (2019, background): “, 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 identification attacks [8, 41].”
Automated Website Fingerprinting through Deep Learning (2017, neutral): “…a realistic large-scale open world setting poses a lot of issues, such as (1) the effect of the hypothesis space complexity, as shown by Panchenko et al. [25], and (2) the base rate fallacy, demonstrated by Juarez et al. [20] for monitored websites with a very low prior probabilities of visit.”
Website Fingerprinting at Internet Scale (2016, methodology): “, the one described in [14]) and is not subject to simplified assumptions made by the related work.”