Autonomous decision on intrusion detection with trained BDI agents

Abstract

In the context of computer security, the first step to respond to an intrusive incident is the detection of such activity in the monitored system. In recent years, research in intrusion detection has evolved to become a multi-discipline task that involves areas such as data mining, decision analysis, agent-based systems or cost–benefit analysis among others. We propose a multiagent IDS that considers decision analysis techniques in order to configure itself optimally according to the conditions faced. This IDS also provides a quantitative measure of the value of the response decision it can autonomously take. Results regarding the well-known 1999 KDD dataset are shown.