Genetic Algorithm Rule Definition for Denial of Services Network Intrusion Detection

作     者：Yong Wang1 2 Dawu Gu1 1. Dept. of computer Science and Engineering Shanghai Jiao Tong University Shanghai China Xiuxia Tian2 Jing Li2 2. Dept. of computer Science and Technology Shanghai University of Electric Power Shanghai China 

会议名称：《2009 International Conference on Computational Intelligence and Natural Computing(CINC 2009)》

会议日期：2009年

学科分类：0839[工学-网络空间安全] 08[工学] 

基　　金：Sponsored by the Hi-Tech Research and Development Program of China under Grant (No. 2006AA01Z405) Shanghai Postdoctoral Scientific Program No. ( No.08R214131) Innovation Program of Shanghai Municipal Education Commission(No. 09YZ346) 

关 键 词：genetic algorithm rule definition denial of services network intrusion detection 

摘      要：Many previous Genetic Algorithm methods can get much better example results in KDD cup 99 dataset. In the real intrusion detection system, the software needs update the rule even everyday. In this paper, we expand previous work and present a fitness function, propose an efficient rule generator for denial of services of network intrusion detection. We use more chromosomes with relevant features and more rule generator. As such, the rules generated by our algorithm are suitable to continuously changing misuse detection. In order to verify our approach, we tested our proposal with KDD Cup99 dataset, The experimental results show that the proposed approach is an efficient way in network intrusion detection.