基于支持向量机的异常入侵检测系统

Abnormal Intrusion Detection System Based on Support Vector Machines

设计并实现了一种基于支持向量机(Support Vector Machines, SVM)的异常入侵检测系统。在先验知识(样本)较少的条件下该系统仍具有良好的推广能力。通过实验将其与神经网络检测模型进行对比,证实采用SVM进行入侵检测的有效性。当检测性能相同时,系统的训练时间大大缩短。

An intrusion detection system based on support vector machine is designed and implemented. The generalizing ability of intrusion detection system is still good when the priori knowledge is less (namely, the sample size is small). Comparison of detection ability between the above detection method and BP neural network shows that the intrusion detection system based on support vector machine can effectively detect intrusion and can dramatically shorten the training time under the same detection performance condition.