Fuzzy Rule Study Model of Network Intrusion Detection System
Yu Li · Jisuanji gongcheng · 2005
This paper analyzes the cause of false-alarm and low detection rate of the intrusion detection systems. From the angle of mending the unprecision problem of detection rules, it creates a fuzzy rule study model for network intrusion detection system. First proveds the equivalence relation of the intrusion actions in the noise environment. From the origin rules of the existing intrusion detection system, creates weight-based fuzzy detection rules. And a feedback study algorithm is proposed, with which it modifies the fuzzy detection rules to get the optimal results of recognition. This model can be easily applied in all kinds of existing ruled-based intrusion detection systems.