An intrusion detection method based on KICA and SVM
Yuancheng Li, Zhongqiang Wang, Yinglong Ma · 2008
Recently, support vector machine (SVM) has become a popular tool in classification, feature extraction is an important step in developing a successful classifier. In this paper, a novel intrusion detection method based on KICA and SVM is proposed. In the proposed method, KICA is applied to extraction features from the raw data set captured from the network, and these features extracted by KICA is used as input data of SVM, which can learn from the input data. Based on the good performance of SVM in generalization, experimental results show that this model can not only detect existed attacks but also new attacks, even the accuracy is improved remarkably.