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 ›› 2011, Vol. 37 ›› Issue (21): 100-101,104. doi: 10.3969/j.issn.1000-3428.2011.21.034

• 安全技术 • 上一篇    下一篇

基于δ-HSSVM的协同入侵检测方法

房小兆,张 巍,滕少华,韩 娜   

  1. (广东工业大学计算机学院,广州510006)
  • 收稿日期:2011-05-23 出版日期:2011-11-05 发布日期:2011-11-05
  • 作者简介:房小兆(1980-),男,硕士研究生,主研发向:网络安全,模式识别;张 巍,副教授、硕士;滕少华,教授、博士;韩 娜,硕士研究生
  • 基金资助:
    广东省自然科学基金资助项目(06021484, 915100900100 0007, 9451009001002777);广东省科技计划基金资助项目(2008A 060201011);广州市越秀区科技计划基金资助项目(2007-GX-075)

Cooperative Intrusion Detection Method Based on δ-HSSVM

FANG Xiao-zhao, ZHANG Wei, TENG Shao-hua, HAN Na   

  1. (Faculty of Computer, Guangdong University of Technology, Guangzhou 510006, China)
  • Received:2011-05-23 Online:2011-11-05 Published:2011-11-05

摘要: 传统入侵检测方法检测速度较慢。为此,提出一种基于δ-超球结构支持向量机的协同入侵检测方法。增加参数δ,以控制超球内样本的数量,按照网络协议产生3类基于δ-超球结构支持向量机的检测代理,以协同的方式对其相应网络数据做出决策。实验结果表明,与单一检测代理方法相比,该方法检测率高、检测时间少。

关键词: 入侵检测, 网络协议, 检测代理, 检测率

Abstract: For the problem of slow detection speed of traditional intrusion detection, δ-hypersphere Structure Support Vector Machine(δ-HSSVM) is presented. The number of samples inside hypersphere are controled by the increasing parameter δ. Three detection agents based on δ-HSSVM generated according to network protocols. And the three detection agents make decisions to the corresponding network data. Experimental results show that, this method has a higher detection rate and less detection time than single detection agent.

Key words: intrusion detection, network protocol, detection agent, detection rate

中图分类号: