关键词: 入侵检测 支持向量机 主动学习

Abstract:

The Intrusion Detection System（I D S） has become an important part of network security. However, the traditional abnormal detection is heavily dependent on the large training samples to get high detection precision, but it is difficult to obtain sufficient training data in a real network environment  . In order to solve the problem of excessive expense caused by obtaining the training samples, we use the SVM（Support Vector Machine）active learning a  algorithm in network intrusion detection. Compared with the traditional self-learning algorithm, our experiment shows that the active learning algorithm can immensely reduce the number of training samples and the training time, thus efficiently improving the performance of classification in IDSs.

Key words: intrusion detection, support vector machine, active learning