Intrusion Detection in Access Control Systems as a Resource Allocation Problem

We study intrusion detection in access control systems as a resource allocation problem, and address it within a decision and control framework. By modeling the interaction between malicious attacker(s) and the intrusion detection system (IDS) as a noncooperative non-zero sum game, we investigate a game theoretic approach for optimal allocation of intrusion detection sensors. In addition, we present an algorithm utilizing linear programming concepts for IDS alert configuration, leading to efficient usage of system administrator’s limited resources. Finally, we implement an IDS prototype for access control in MATLAB utilizing anomaly detection sensors based on self-organizing maps, and demonstrate its operation under various scenarios.