Corpus ID: 62841568

Adv-DWF: Defending Against Deep-Learning-Based Website Fingerprinting Attacks with Adversarial Traces

@article{Imani2019AdvDWFDA,
  title={Adv-DWF: Defending Against Deep-Learning-Based Website Fingerprinting Attacks with Adversarial Traces},
  author={M. Imani and Mohammad Saidur Rahman and Nate Mathews and Aneesh Yogesh Joshi and M. Wright},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.06626}
}
Website Fingerprinting (WF) is a type of traffic analysis attack that enables a local passive eavesdropper to infer the victim's activity even when the traffic is protected by encryption, a VPN, or some other anonymity system like Tor. Leveraging a deep-learning classifier, a WF attacker can gain up to 98% accuracy against Tor. Existing WF defenses are either too expensive in terms of bandwidth and latency overheads (e.g. 2-3 times as large or slow) or ineffective against the latest attacks. In… Expand
1 Citations

References

SHOWING 1-10 OF 45 REFERENCES
Deep Fingerprinting: Undermining Website Fingerprinting Defenses with Deep Learning
Bayes, not Naïve: Security Bounds on Website Fingerprinting Defenses
Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks
Practical Black-Box Attacks against Machine Learning
Toward an Efficient Website Fingerprinting Defense
Fingerprinting Attack on Tor Anonymity using Deep Learning
Towards Deep Learning Models Resistant to Adversarial Attacks
Glove: A Bespoke Website Fingerprinting Defense
...
1
2
3
4
5
...