Oriental Journal of Computer Science and Technology

Noria Benyettou ¹, Abdelkader Benyettou ¹, Vincent Rodin ², Souad Yahia Berrouiguet ³

Affiliations
1 Laboratoire SIMPA, Universitedes Sciences et Technologie d'Oram, Mohammed Boudiaf, BP 1505, Oran, DZ
2 European University of Brittany, UBO, EA3883, LISyC, CS 93837, 29238 Brest Cedx3, FR
3 National Institute of Telecommunications and Information Technology and Communication, INTTIC, Senia Street, Elm'naouar, Oran Algéria, DZ

Abstract

Network intrusion detection Systems are designed to protect computer networks by observing frames and notifying the operators when a possible attack happened. But with the development of network and the information exchange, networks became increasingly vulnerable faced at the new forms of threats. It is necessary to improve the performance of an intrusion detection system. Inspired by immune biological system behavior and the performances of the multi-agent systems, we present in this article a new model (MAISID) of multi-agent system immune for intrusion detection. MAISID is a system that performs frames analyses by a group of immune agents’ collaboration. These agents are distributed on the network to achieve simultaneous treatments, and are auto-adaptable to the evolution of the environment and have also the property of communication and coordination in order to ensure a good detection of intrusions in a distributed network. In this approach, the MAISID model is installed in each host of the network and sub-network for an extensive monitoring and a simultaneous analysis of the frames.

Keywords

Intrusion Detection System, Artificial Immune System, Multi-Agents System, Network Security.

Full Text