Robust Real-time Intrusion Detection System

Computer security has become a critical issue with the rapid development of business and other ftansaction systems over the Intemet. The application of atlificial intelligence, machine learning and data mining techdques to intrusion detection systems has been increasing recently. But most research is focused on improving the classification performaace of a classifier. Selecting important features from input data leads to simplification olthe problem, and faster and more accuate detection rates. Thus selecting important features is ar impofiant issue in intrusion detection. Alother issue in intrusion detection is that inost of the intrusion detection systems are performed by offJine and it is not a suitable method for a real-time intrusion detection system. In this paper, we develop the real-time intrusion detection system, which combines an online feature extraction method with the Least Squares Suppofi Vector Machine classifier. Applying the proposed system to KDD CUP 99 data, experimental results show that it has a remarkable feature extraction and classification performance compared to existing off-line intntsion detection systems.