论文标题
盲人网络扰动
Blind Adversarial Network Perturbations
论文作者
论文摘要
深度神经网络（DNN）通常用于各种流量分析问题，例如网站指纹和流相关性，因为它们的表现优于传统（例如统计）技术，而大幅度的较大利润率则超过了传统的（例如统计）技术。但是，已知深层神经网络容易受到对抗性示例的影响：由于小小的对抗性扰动而导致模型错误地标记的模型的对抗性输入。在本文中，我们首次表明，对手可以通过在\ emph {live}网络流量的模式上应用\ emph {对抗性扰动}来打败基于DNN的流量分析技术。
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.
