AdvTG: An Adversarial Traffic Generation Framework to Deceive DL-Based Malicious Traffic Detection Models
Deep learning-based (DL-based) malicious traffic detection models are effective but vulnerable to adversarial attacks. Existing adversarial attacks have shown promising results when targeting traffic detection models based on statistics and sequence features. However, these attacks are less effective against models that rely on payload analysis. The main reason is the difficulty in generating semantic, compliant, and functional payloads, which limits their practical application.
Authors
- Xiaochun Yun (ORCID: https://orcid.org/0000-0003-2849-1086)
- Peishuai Sun (ORCID: https://orcid.org/0000-0003-1135-8297)
- Chengxiang Si (ORCID: https://orcid.org/0000-0003-2646-6100)
- Shuhao Li (ORCID: https://orcid.org/0000-0001-6071-5284)
- Jiang Xie (ORCID: https://orcid.org/0000-0003-3219-3102)
- Tao Yin
Institutions
- National Computer Network Emergency Response Technical Team/Coordination Center of Chinar (CN)
- Institute of Information Engineering (CN)
- University of Chinese Academy of Sciences (CN)
Publication Details
- Published
- 2025-04-22
- DOI
- https://doi.org/10.1145/3696410.3714876
- Citations
- 6
- Primary Topic
- Network Security and Intrusion Detection
- Type
- article
- Field-Weighted Citation Impact
- 8.92