Intrusion Detection Based on TSVM and Feature Selection

In this paper, we propose a new network intrusion detection method based on TSVM (Transductive Support Vector Machines) classification algorithm and hybrid feature selection approach. It can effectively detect anomalies with high detection rate and low false positives. Experimental results on the well-known KDD Cup 1999 dataset demonstrate the proposed method is robust and more effective than the state-of-the-art intrusion detection method.