Learning to Detect Cyber Attacks: Neural Anomaly Detection for Cybersecurity with Theoretical Insights

תקציר מקורי באנגליתarXiv:2409.08521v2 Announce Type: replace-cross Abstract: In cybersecurity practice, new forms of cyberattacks continuously emerge, deliberately designed to evade defense systems that rely on previously observed behaviors. Motivated by this challenge, we propose a neural network-based method for anomaly detection that does not rely on (1) prior knowledge of anomaly distributions or (2) the availability of real anomalies during training. Our proposed method trains a neural network classifier using only normal samples, combining the supervision from synthetic anomalies, and is particularly suitable when collecting real anomaly samples is expensive or impractical. The trained classifier is proven to attain minimax excess risk, and more importantly, it is guaranteed to learn the boundary of th