基于kNN算法的异常行为检测方法研究  

Research on Abnormal Behavior Detection Based on kNN Algorithm

作　　者：卢鋆[1] 吴忠望[1] 王宇[1] 卢昱[1] 

机构地区：[1]装备指挥技术学院研究生院,北京101416

出　　处：《计算机工程》2007年第7期133-134,138,共3页Computer Engineering

基　　金：国家"863"计划基金资助项目(2005AA149010)

摘　　要：阐述了异常行为检测的相关概念,介绍了kNN算法,探讨了异常行为检测与分类技术的关系。结合kNN算法的优点以及异常行为检测与分类的相似性,提出了基于kNN算法的异常行为检测方法,给出了其计算方法,并确定了检测的过程,分析了该方法的特点和优势。基于kNN算法的异常行为检测方法通过不断的自学习,会成为信息安全的一道有效防线。This paper elaborates the concepts related to abnormal behavior detection, introduces kNN algorithm and discusses the relationship between abnormal behavior detection and classification technologies. Based on the virtues of kNN algorithm and the comparability between abnormal behavior detection and classification, the method of abnormal behavior detection based on kNN algorithm is proposed and its calculation method and detection process is given. After analyzing its characteristics and advantages, it concludes that the method of abnormal behavior detection based on kNN will become an effective delense tne of information security through continuous self-study.

关 键 词：KNN算法 分类 异常行为检测 

分 类 号：TP393.01[自动化与计算机技术—计算机应用技术]