Application of genetic algorithm in rule extraction of intrusion detection
Dongli Zhang · Ha'erbin gongye daxue xuebao · 2009
The attack rule base of traditional intrusion detection systems were built manually.An adaptive method based on genetic algorithms was presented for learning the intrusion detection rules in order to realize the automation of attack rule generation.The genetic algorithm was employed to derive a set of classification rules from network audit data,and the support-confidence framework was utilized as fitness function to judge the quality of each rule.The generated rules were then used to detect or classify network intrusions in a real-time environment.The experiment proves the efficiency of the presented method.