GANDaLF: GAN for Data-Limited Fingerprinting
| Autor: | Nicholas Hopper, Nate Mathews, Mohammad Saidur Rahman, Matthew Wright, Se Eun Oh |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Data limited
Ethics 021110 strategic defence & security studies Computer science 0211 other engineering and technologies 020206 networking & telecommunications 02 engineering and technology QA75.5-76.95 computer.software_genre BJ1-1725 Gandalf Electronic computers. Computer science 0202 electrical engineering electronic engineering information engineering Operating system General Earth and Planetary Sciences computer General Environmental Science |
| Zdroj: | Proceedings on Privacy Enhancing Technologies, Vol 2021, Iss 2, Pp 305-322 (2021) |
| ISSN: | 2299-0984 |
| Popis: | We introduce Generative Adversarial Networks for Data-Limited Fingerprinting (GANDaLF), a new deep-learning-based technique to perform Website Fingerprinting (WF) on Tor traffic. In contrast to most earlier work on deep-learning for WF, GANDaLF is intended to work with few training samples, and achieves this goal through the use of a Generative Adversarial Network to generate a large set of “fake” data that helps to train a deep neural network in distinguishing between classes of actual training data. We evaluate GANDaLF in low-data scenarios including as few as 10 training instances per site, and in multiple settings, including fingerprinting of website index pages and fingerprinting of non-index pages within a site. GANDaLF achieves closed-world accuracy of 87% with just 20 instances per site (and 100 sites) in standard WF settings. In particular, GANDaLF can outperform Var-CNN and Triplet Fingerprinting (TF) across all settings in subpage fingerprinting. For example, GANDaLF outperforms TF by a 29% margin and Var-CNN by 38% for training sets using 20 instances per site. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|