基于相空间重构和一类分类的异常入侵检测

Anomalydetection based on Phase Space Reconstruction and Oneclass Classification

结合相空间重构理论与一类分类方法提出网络异常入侵检测方法。该方法首先将网络数据序列映射到相空间 ,然后对相空间中的数据点实行一类分类。最后根据 KKT条件进行异常检测。仿真实验结果表明了该方法的可行性和有效性。

A new method of network anomaly intrusion detection is proposed in this paper,which is based on phase space reconstruction theory and oneclass classification method.The method first maps network data to phase space,and then obtains a distinguish function by oneclass classification in phase space,finally anomalydetection is processed based on KKT conditions.The results of simulation experiments show the feasibility and effectiveness of the method.