Journal of Computer Applications ›› 2012, Vol. 32 ›› Issue (09): 2606-2608.DOI: 10.3724/SP.J.1087.2012.02606

• Information security • Previous Articles     Next Articles

Intrusion detection model based on LISOMAP relevant vector machine

TANG Chao-wei,LI Chao-qun*,YAN Kai,YAN Ming   

  1. College of Communication Engineering,Chongqing University,Chongqing 400030,China
  • Received:2012-03-01 Revised:2012-04-27 Online:2012-09-01 Published:2012-09-01

基于LISOMAP的相关向量机入侵检测模型

唐朝伟,李超群*,燕凯,严鸣   

  1. 重庆大学 通信工程学院,重庆 400030
  • 通讯作者: 李超群
  • 作者简介:唐朝伟(1966-),男,四川达州人,教授,博士,CCF会员,主要研究方向:宽带移动多媒体通信、互联网内容识别及处理、分布式网络安全及抗毁路由; 李超群(1985-),男,河北唐山人,硕士研究生,主要研究方向:分布式防火墙及路由抗毁; 燕凯(1989-),男,山东淄博人,硕士研究生,主要研究方向:分布式网络安全; 严鸣(1988-),男,陕西安康人,硕士研究生,主要研究方向:分布式网络安全。
  • 基金资助:

    国家科技重大专项基金资助项目(2009ZX03004-002)

Abstract: Concerning low classification accuracy and high false alarm rate of current intrusion detection models, an intrusion detection classification model based on Landmark ISOmetric MAPping (LISOMAP) and Deep First Search (DFS) Relevant Vector Machine (RVM) was proposed. The LISOMAP was adopted to reduce the dimension of the training data, and RVM based on the DFS was used for classification detection. Compared with the Principal Components Analysis (PCA)-Supported Vector Machine (SVM), the experimental results indicate that the LISOMAP-DFSRVM model has lower false alarm rate with almost the same detection rate.

Key words: intrusion detection, Principal Component Analysis (PCA), Support Vector Machine (SVM), Landmark ISOmetric MAPping (LISOMAP), Relevant Vector Machine (RVM), Deep First Search (DFS)

摘要: 针对现有入侵检测模型分类检测精度低、误报率高的问题,提出一种基于地标等距映射(LISOMAP)的相关向量机(RVM)入侵检测分类模型。首先采用LISOMAP对训练样本中的数据进行非线性降维,结合深度优先搜索(DFS)参数优化的RVM进行分类检测。结果表明,该模型与基于主成分分析(PCA)法的支持向量机(SVM)、基于LISOMAP的SVM模型相比,在保证一定检测率的情况下,误报率有了明显下降。

关键词: 入侵检测, 主成分分析, 支持向量机, 地标等距映射, 相关向量机, 深度优先搜索

CLC Number: