Intrusion Detection System Based on Integration of Soft Computing Techniques

Abstract

Soft computing techniques are more and more widely used to solve a variety of practical problems. This paper applied the integration of different soft computing techniques in intrusion detection system(IDS). Due to the increasing incidents of network attacks, building effective intrusion detection system is necessary, but it faces great challenges. Two sorts of soft computing techniques are studied:Artificial Neural Network (ANN) and Support Vector Machines(SVM). Experimental results show that integration of ANN and SVM is superior to individual approaches for intrusion detection in terms of classification accuracy.