Blind Adversarial Network Perturbations
arXiv:2002.06495
Abstract
Deep Neural Networks (DNNs) are commonly used for various traffic analysis problems, such as website fingerprinting and flow correlation, as they outperform traditional (e.g., statistical) techniques by large margins. However, deep neural networks are known to be vulnerable to adversarial examples: adversarial inputs to the model that get labeled incorrectly by the model due to small adversarial perturbations. In this paper, for the first time, we show that an adversary can defeat DNN-based traffic analysis techniques by applying \emph{adversarial perturbations} on the patterns of \emph{live} network traffic.
References in corpus (7)
- Intriguing properties of neural networks
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
- RAPTOR: Routing Attacks on Privacy in Tor
- EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
- Practical Traffic Analysis Attacks on Secure Messaging Applications
- Universal Adversarial Audio Perturbations