You do (not) belong here

Zhu, Shitong; Li, Shasha; Wang, Zhongjie; Chen, Xun; Qian, Zhiyun; Krishnamurthy, Srikanth V.; Chan, Kevin; Swami, Ananthram

doi:10.1145/3386367.3431311

Cited by 12 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Metrics. We mainly use AUC and F1 score because they are most widely used in the literature [8], [20], [30], [35], [56], [75], [91]. Also, we use other six metrics to validate the improvements of HyperVision, including precision, recall, F2, ACC, FPR, and EER.…”

Section: • Deeplog (Event Based Recording and DL Based Detection)mentioning

confidence: 99%

Detecting Unknown Encrypted Malicious Traffic in Real Time via Flow Interaction Graph Analysis

Fu¹,

Li²,

Xu³

2023

Proceedings 2023 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

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 stateof-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.

show abstract