Multi-softman智能入侵防御系统的研究  

Multi-softman-based intelligence intrusion prevention system

作　　者：马占飞[1,2] 郑雪峰[2] 

机构地区：[1]内蒙古科技大学包头师范学院,内蒙古包头014030 [2]北京科技大学信息工程学院,北京100083

出　　处：《计算机应用研究》2009年第4期1503-1505,1508,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(60375038);北京市自然科学基金资助项目(4072018);内蒙古教育厅自然科学基金资助项目(NJZY07116);内蒙古高等院校青年基金资助项目(BS2006012028)

摘　　要：针对传统入侵检测技术难以适应大流量、高带宽的动态网络环境的局限性,在对软件人(SM)的基本理论和智能特性研究基础上,受其启发提出了基于群体软件人(MSM)的智能入侵防御系统协作控制模型。模型采取无控制中心的群体软件人分布式体系结构,避免了单个中心分析器带来的单点失效问题;同时该系统还充分利用了软件人智能协商控制机制,有效地解决信任社区内与社区间的协同预警及防御问题,也为网络安全防范提供了新的研究思路。Through analyzing and studying the characteristics of large-scale network intrusion detection system （ IDS）, dis- cussed some crucial disadvantages of the existing IDS briefly. Inspired by the intelligence recognition capability of SM, proposed a novel and visual muhi-softman intrusion prevention system （MSMIPS） cooperation model. In order to reduce the relativity of each detection components as far as possible and avoid the single point failure caused by the single central analyzer, the model is adopted the non-control center muhi-softman（MSM） distributed architecture. At the samd time, MSMIPS enables member sites in the same trust community or different ones to forewarn attacks cooperatively. Thus, MSMIPS had some merits, such as higher detection rate, load balance and better self-adaptabihty, and so on. MSMIPS also provided a novel way for implementa- tion of network security.

关 键 词：软件人 人工智能 代理 入侵检测系统 入侵防御系统 协商控制 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]