作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (07): 133-134. doi: 10.3969/j.issn.1000-3428.2007.07.048

• 安全技术 • 上一篇    下一篇

基于kNN算法的异常行为检测方法研究

卢 鋆,吴忠望,王 宇,卢 昱   

  1. (装备指挥技术学院研究生院,北京 101416)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-04-05 发布日期:2007-04-05

Research on Abnormal Behavior Detection Based on kNN Algorithm

LU Jun, WU Zhongwang, WANG Yu, LU Yu   

  1. (Graduate School, Academy of Equipment Command and Technology, Beijing 101416)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-04-05 Published:2007-04-05

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。

关键词: kNN算法, 分类, 异常行为检测

Abstract: 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 defense line of information security through continuous self-study.

Key words: kNN algorithm, Classification, Abnormal behavior detection