Contrast Duality of Adversarial Learningin Network Intrusion: A Review

Summary

This review surveys adversarial learning in network intrusion detection, covering data poisoning, test time evasion, and reverse engineering as offensive threats. It also examines adversarial training as a defense mechanism. The authors identify research gaps, including the scarcity of real-life attack data and limited evaluation of AI-based solutions for network traffic.

Related items

• LowYour Robot's Safety Functions Already Work. What If the Input Lies?Similar attack · VicOne Blog
• LowMeasuring Robustness and Efficiency in a Connectome-Constrained Fly Visual System Model: Linking an Adversarial and a Perceptual IllusionSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoStructured Confidence Perturbation via Fisher Geometry for Adversarial TrainingSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoA Layer-wise Study of How Style Rewriting Breaks the Calibration of Zero-Shot LLM Fake-News DetectorsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoEvaluating the robustness of explainable AI methods to adversarial attacks in intrusion and malware detectionSimilar attack · OpenAlex (peer-reviewed AI security)