Abstract: Following ENISA's findings on the two main trends in Cyber Defence development over the past few years - adopting the philosophy and methods of Military Intelligence and introducing Artificial Intelligence into technologies for counteraction of cyber attacks was made research on the application of intelligent methods for increasing the security in computer networks. Penetration is defined as a set of actions to compromise the integrity, confidentiality, and availability of resources. This paper introduces a model for Intrusion detection/prevention system based on multi-agent systems. Results of simulation are presented and a comparison is made of the performance of the system compared to others.

Keywords: multi-agent systems, security, intrusion detection system, intrusion prevention system.