Genetic-clustering algorithm for intrusion detection system

Abstract

This study proposes a genetic-clustering algorithm to etect and classify the data instances, collected from intrusion detection systems into normal or attack clusters, automatically. The proposed genetic clustering algorithm can obtain the optimal clustering solution based on the minimum distance of within cluster distance and maximum distance of between cluster distance. The two main aims of the proposed algorithm are to increase the detection rate and decrease the false negative rate for intrusion detection systems. The experimental results show that the proposed approach can reach available rate levels for detection rate, false negative rate, and the novel attack detection rate. © 2008, Inderscience Publishers.