Few-shot website fingerprinting attack

Chen, Mantun; Wang, Yongjun; Xu, Hongzuo; Zhu, Xiatian

doi:10.1016/j.comnet.2021.108298

Cited by 23 publications

(14 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the anonymized network traffic data of the single webpage as the input, different WF attacks have been proposed. They can be mainly divided into three categories: traditional ST-WFA [4][5][6][9][10][11], deep learning based ST-WFA [3,7,8,12] and few-shot ST-WFA [13][14][15].…”

Section: Single-tab Wf Attackmentioning

confidence: 99%

“…Deep models often need a large number of training data, which could be difficult to collect in many cases. To overcome this challenge, few-shot learning has been introduced with representative works including TF [13], TLFA [14], and HDA [15]. In particular, TLFA can achieve over 90% accuracy with only one sample per new website through knowledge reuse of seen websites.…”

Section: Single-tab Wf Attackmentioning

confidence: 99%

“…As a result, there are a total of 18 different overlapping types. With the single-tab traces from DS-19 ATTACKTRAIN , we generate 9900 × 18/ -tab traces for each ∈ [2,5,8,11,14,17] and the overlapping types are randomly selected. With the base rate r = 10, there are 900 × 18 single monitored traces and 9000 × 18 single unmonitored traces for every case.…”

Section: Datasets and Protocolsmentioning

confidence: 99%

“…The 100way 20-shot performance means that, with 100 new websites of AWF te , we freeze the feature extractor and only fine-tune its classifier with only 20 samples per website, and test the finetuned model in the closed-world scenario in which another 15 samples per website are randomly chosen. Except for the input of a 512-length burst sequence, we follow the same training and test setting of Chen [14], with the logistic regression classifier. About the baseline TLFA [14], we choose the 5000length cell sequence as input, DF [8] as the feature extractor, and the logistic regression as the classifier.…”

Section: Lightweight Pre-trained Feature Extractormentioning

confidence: 99%

“…However, by observing the side-channel pattern without decryption on any one of the on-path routers before entering Tor's entry proxy, an attacker could still compromise a user's browsing privacy via traffic analysis, i.e., website fingerprinting attack (WFA). In the past decade, an extensive number of existing studies [3][4][5][6][7][8][9][10][11][12] have achieved remarkable success, even with only a few training samples per website [13][14][15].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

End-to-End Multi-Tab Website Fingerprinting Attack: A Detection Perspective

Chen¹,

Chen²,

Wang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Website fingerprinting attack (WFA) aims to deanonymize the website a user is visiting through anonymous networks channels (e.g., Tor). Despite of remarkable progress in the past years, most existing methods make implicitly a couple of artificial assumptions that (1) only a single website (i.e., single-tab) is visited each time, and (2) website fingerprinting data are pre-trimmed into a single trace per website manually. In reality, a user often open multiple tabs for multiple websites spontaneously. Indeed, this multi-tab WFA (MT-WFA) setting has been studied in a few recent works, but all of them still fail to fully respect the real-world situations. In particular, the overlapping challenge between website fingerprinting has never been investigated in depth. In this work, we redefine the problem of MT-WFA as detecting multiple monitored traces, given a natural untrimmed traffic data including monitored traces, unmonitored traces, and potentially unconstrained overlapping between them. This eliminates the above assumptions, going beyond the conventional single website fingerprint classification perspective taken by all previous WFA methods. To tackle this realistic MT-WFA problem, we formulate a novel Website Fingerprint Detection (WFD) model capable of detecting accurately the start and end points of all the monitored traces and classifying them jointly, given long, untrimmed raw traffic data. WFD is end-to-end, with the trace localization and website classification integrated in a single unified pipeline. To enable quantitative evaluation in our MT-WFA setting, we introduce new performance metrics. Extensive experiments on several newly constructed benchmarks show that our WFD outperforms the state-of-the-art alternative methods in both accuracy and efficiency by a large margin, even with a very small training set. Code is available at https://github.com/WFDetector/WFDetection.

show abstract