基于特征选择的无监督入侵检测方法  

Unsupervised intrusion detection based on feature selection

作　　者：吴剑[1] 

机构地区：[1]山东政法学院信息科学技术系,济南250014

出　　处：《计算机工程与应用》2011年第26期79-82,共4页Computer Engineering and Applications

基　　金：山东省高等学校科技计划项目(No.J09LG62)

摘　　要：为提高入侵检测系统的检测速度和效果,结合遗传算法提出了一种基于特征选择的无监督入侵检测方法。一方面利用改进的遗传算法作为搜索策略;一方面使用K均值聚类算法对提取特征后的数据进行聚类,并将类间离散度和类内离散度的相关比值作为特征子集的评价指标,从而实现最优特征子集的求解并用于无监督的入侵检测。实验结果表明,该方法由于解决了入侵检测的特征选择问题,与未采用特征选择的无监督入侵检测相比具有更好的性能。In order to improve performances of intrusion detection system in terms of detection speed and detection rate,a novel unsupervised intrusion detection method based on Genetic Algorithm（GA） and feature selection mechanism is proposed.In the method,an improved GA is adopted as search strategy.On the other hand,the K-means clustering is used to classify the feature data,whose evaluation target is the ratio of the between-class scatter to the within-class scatter.Then,the optimal feature subset is found and applied to unsupervised intrusion detection.The experimental results show that the method can solve the feature selection problem of intrusion detection effectively,and it has a better detecting effect than unsupervised intrusion detection without feature selection.

关 键 词：遗传算法 K均值聚类 入侵检测 特征选择 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]