Chuanpu Fu (Tsinghua University), Qi Li (Tsinghua University), Ke Xu (Tsinghua University)

Nowadays traffic on the Internet has been widely encrypted to protect its confidentiality and privacy. However, traffic encryption is always abused by attackers to conceal their malicious behaviors. Since the encrypted malicious traffic has similar features to benign flows, it can easily evade traditional detection methods. Particularly, the existing encrypted malicious traffic detection methods are supervised and they rely on the prior knowledge of known attacks (e.g., labeled datasets). Detecting unknown encrypted malicious traffic in real time, which does not require prior domain knowledge, is still an open problem.

In this paper, we propose HyperVision, a realtime unsupervised machine learning (ML) based malicious traffic detection system. Particularly, HyperVision is able to detect unknown patterns of encrypted malicious traffic by utilizing a compact inmemory graph built upon the traffic patterns. The graph captures flow interaction patterns represented by the graph structural features, instead of the features of specific known attacks. We develop an unsupervised graph learning method to detect abnormal interaction patterns by analyzing the connectivity, sparsity, and statistical features of the graph, which allows HyperVision to detect various encrypted attack traffic without requiring any labeled datasets of known attacks. Moreover, we establish an information theory model to demonstrate that the information preserved by the graph approaches the ideal theoretical bound. We show the performance of HyperVision by real-world experiments with 92 datasets including 48 attacks with encrypted malicious traffic. The experimental results illustrate that HyperVision achieves at least 0.92 AUC and 0.86 F1, which significantly outperform the state-of-the-art methods. In particular, more than 50% attacks in our experiments can evade all these methods. Moreover, HyperVision achieves at least 80.6 Gb/s detection throughput with the average detection latency of 0.83s.

View More Papers

Enhanced Vehicular Roll-Jam Attack using a Known Noise Source

Zachary Depp, Halit Bugra Tulay, C. Emre Koksal (The Ohio State University)

Read More

Blaze: A Framework for Interprocedural Binary Analysis

Matthew Revelle, Matt Parker, Kevin Orr (Kudu Dynamics)

Read More

Applying Accessibility Metrics to Measure the Threat Landscape for...

John Breton, AbdelRahman Abdou (Carleton University)

Read More

Machine Unlearning of Features and Labels

Alexander Warnecke (TU Braunschweig), Lukas Pirch (TU Braunschweig), Christian Wressnegger (Karlsruhe Institute of Technology (KIT)), Konrad Rieck (TU Braunschweig)

Read More