Layered approach for intrusion detection systems based genetic algorithm

Abstract

An intrusion detection system monitors the activities of a given environment and determines whether these activities are malicious or legitimate (normal) based on system integrity, confidentiality and the availability of information resources. This work proposes a methodology to overcome all the weakness of single layer intrusion detection. In this work, a layered approach for intrusion detection is proposed which is based on genetic algorithm. In this model, the four layers correspond to four attack groups. They are Probe, DOS, R2L and U2R attacks. But in this approach, there is no mathematical method for calculating filter parameters for DOS, R2L, U2R attacks. So, we present a new approach which is genetic algorithm based, for calculating those parameters to make the system more secure. This efficiently detect R2L attack and 90 % accuracy detected.