Intrusion detection using optimal genetic feature selection and SVM based classifier

In the recent years, the rapid advancement of computer networks has led to many security problems by malicious users to the modern computer systems. Hence, it is necessary to detect illegitimate users by monitoring the unusual user activities in the network. In this paper, we propose an Intrusion Detection System (IDS) which uses a genetic algorithm based feature selection approach and a Support vector machine based classification algorithm. The combination of feature selection using the newly proposed genetic feature selection algorithm with Support Vector Machine based classification gives better results than other exiting methods. This is due to the fact that the proposed feature selection algorithm enhances the performance of the classifier in detecting the attacks by providing the most useful attributes. This IDS is more efficient in detecting the attacks and it effectively reduces the false alarm rate.