Adaptive Fingerprinting: Website Fingerprinting over Few Encrypted Traffic
Adaptive Fingerprinting: Website Fingerprinting over Few Encrypted Traffic
复制标题
DOI：
10.1145/3422337.3447835
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Chenggang Wang;Jimmy Dani;Xiang Li;Xiaodong Jia;Boyang Wang
中科院分区：
文献类型：
--
作者：
Chenggang Wang;Jimmy Dani;Xiang Li;Xiaodong Jia;Boyang Wang
网站指纹攻击可以推断用户通过加密的网络流量访问哪个网站。最近的研究可以通过利用深度神经网络来实现高精度(例如，98%)。然而，目前的攻击依赖于大量加密的流量数据，收集这些数据非常耗时。而且，大规模的加密流量数据也需要频繁回收，以调整网站内容的变化。换句话说，进行网站指纹识别的引导时间是不现实的。在本文中，我们提出了一种新的方法，称为自适应指纹，它可以利用敌对域的自适应在较少的加密流量上获得高的攻击准确率。使用我们的方法，攻击者只需要收集很少的流量，而不是大规模的数据集，这使得网站指纹在现实世界中更加实用。我们在多个数据集上的大量实验结果表明，在封闭环境下，我们的方法可以在少量加密流量的情况下获得89%的准确率，而在开放世界环境下，我们的方法可以达到99%的准确率和99%的召回率。与最近的一项研究(命名为Triplet指纹)相比，我们的方法在预训练时间上要高效得多，并且更具可扩展性。此外，在封闭世界评价和开放世界评价中，我们的方法的攻击性能都优于三重指纹。
Website fingerprinting attacks can infer which website a user visits over encrypted network traffic. Recent studies can achieve high accuracy (e.g., 98%) by leveraging deep neural networks. However, current attacks rely on enormous encrypted traffic data, which are time-consuming to collect. Moreover, large-scale encrypted traffic data also need to be recollected frequently to adjust the changes in the website content. In other words, the bootstrap time for carrying out website fingerprinting is not practical. In this paper, we propose a new method, named Adaptive Fingerprinting, which can derive high attack accuracy over few encrypted traffic by leveraging adversarial domain adaption. With our method, an attacker only needs to collect few traffic rather than large-scale datasets, which makes website fingerprinting more practical in the real world. Our extensive experimental results over multiple datasets show that our method can achieve 89% accuracy over few encrypted traffic in the closed-world setting and 99% precision and 99% recall in the open-world setting. Compared to a recent study (named Triplet Fingerprinting), our method is much more efficient in pre-training time and is more scalable. Moreover, the attack performance of our method can outperform Triplet Fingerprinting in both the closed-world evaluation and open-world evaluation.