Research on application of support vector machine in intrusion detection

Abstract

There are some problems such as the high false negative rate and false positive rate in intrusion detection technology. The paper researches on the technology of intrusion detection based on support vector machine. The forming process of SVM classifier is analyzed. The choice of kernel function is discussed. The experimental results show that the SVM-based intrusion detection system with the appropriate kernel function has high detection-accuracy and it can effectively predict and classify the network attacks.