Introducing a Classification Model Based on SVM for Network Intrusion Detection

Intrusion Detection Systems are designed to provide security into computer networks. In this article, we used rough sets theory for feature selection to enhance support vector machine in intrusion detection. Testing and evaluation of the proposed method has been performed mainly on NSL-KDD data sets as a corrected version of KDD-CUP99. Experimental results indicate that the proposed method shows a good performance in providing high precision, intrusion detection readout, less error notification rate and more detailed detection compared to its basic and simpler methods.