Few-Shot Website Fingerprinting Attack with Data Augmentation
Open Access
- 15 September 2021
- journal article
- research article
- Published by Wiley in Security and Communication Networks
- Vol. 2021, 1-13
Abstract
This work introduces a novel data augmentation method for few-shot website fingerprinting (WF) attack where only a handful of training samples per website are available for deep learning model optimization. Moving beyond earlier WF methods relying on manually-engineered feature representations, more advanced deep learning alternatives demonstrate that learning feature representations automatically from training data is superior. Nonetheless, this advantage is subject to an unrealistic assumption that there exist many training samples per website, which otherwise will disappear. To address this, we introduce a model-agnostic, efficient, and harmonious data augmentation (HDA) method that can improve deep WF attacking methods significantly. HDA involves both intrasample and intersample data transformations that can be used in a harmonious manner to expand a tiny training dataset to an arbitrarily large collection, therefore effectively and explicitly addressing the intrinsic data scarcity problem. We conducted expensive experiments to validate our HDA for boosting state-of-the-art deep learning WF attack models in both closed-world and open-world attacking scenarios, at absence and presence of strong defense. For instance, in the more challenging and realistic evaluation scenario with WTF-PAD-based defense, our HDA method surpasses the previous state-of-the-art results by nearly 3 in classification accuracy in the 20-shot learning case. An earlier version of this work Chen et al. (2021) has been presented as preprint in ArXiv (https://arxiv.org/abs/2101.10063).Keywords
Funding Information
- Natural Science Foundation of Hunan Province (2021JJ40682, 2018YFB0204301, 61472439)
- National Key Research and Development Program of China (2021JJ40682, 2018YFB0204301, 61472439)
- National Natural Science Foundation of China (2021JJ40682, 2018YFB0204301, 61472439)
This publication has 33 references indexed in Scilit:
- Tri-Training for authorship attribution with limited training data: a comprehensive studyNeurocomputing, 2016
- Deep learningNature, 2015
- A Critical Evaluation of Website Fingerprinting Attacks2014
- A Systematic Approach to Developing and Evaluating Website Fingerprinting Defenses2014
- Improved website fingerprinting on Tor2013
- Website fingerprinting in onion routing based anonymization networks2011
- Inferring the source of encrypted HTTP connections2006
- Privacy Vulnerabilities in Encrypted HTTP Streams2006
- Fingerprinting Websites Using Traffic Analysis2003
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998