J4

• 计算机科学 • 上一篇    下一篇

基于SVM的在线无监督入侵检测系统

张 丹, 任 斐, 赵 阔, 张园园, 刘晓博, 任维武, 胡 亮   

  1. 吉林大学 计算机科学与技术学院, 长春 130012
  • 收稿日期:2008-06-01 修回日期:1900-01-01 出版日期:2009-03-26 发布日期:2009-03-26
  • 通讯作者: 胡 亮

A SVMbased System for Online Unsupervised Intrusion Detection

ZHANG Dan, REN Fei, ZHAO Kuo, ZHANG Yuan yuan,LIU Xiaobo, REN Weiwu, HU Liang   

  1. College of Computer Science and Technology, Jilin University, Changchun 130012, China
  • Received:2008-06-01 Revised:1900-01-01 Online:2009-03-26 Published:2009-03-26
  • Contact: HU Liang

摘要: 针对已有的审计日志, 在使用具有实时数据处理能力的频度加权算法计算私有程序运行时, 对每个进程中相异系统调用的频度取值. 将得到的进程向量集合进行线性扫描, 再根据向量间的距离关系为进程向量添加表示数据“正常”或“异常”标号, 在无人为干预的情况下取得SVM(Support Vector Machine)训练数据. 最后通过支持向量机计算用于监测目标系统的程序正常行为轮廓, 从而构造一个切实可行的在线且无 需人为干预的入侵检测系统.

关键词: 入侵检测, 频度加权, 线性扫描, 支持向量机

Abstract: Using frequency weighting mining algorithm with realtime data processing capability to calculate each system call’s frequency value for existed audit records, we got a vector set of progresses. The vector set was linearly scanned and its progresses were labeled as “normal” or “attack” according to their distance relations. Then, we got a SVM training set without manmade supervision. Finally, the normal behavior profiles for monitoring the target system were generated by SVM classifier so as to construct a practicalon line intrusion detection system without human intervention.

Key words: intrusion detection, frequency weighting, linear scan, support vector machines

中图分类号: 

  • TP309