免疫入侵检测多形态检测算法  

A multi-shape detection algorithm for immunity-based intrusion detection systems

作　　者：席亮[1] 张凤斌[1] 刘海龙[1] 

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080

出　　处：《高技术通讯》2014年第1期16-22,共7页Chinese High Technology Letters

基　　金：国家自然科学基金(60671049;61172168)资助项目

摘　　要：针对基于免疫机制的入侵检测系统的单一形态检测器检测性能低下的问题,分析了二进制形态空间和实值形态空间各自的不足,借鉴免疫独特型网络理论和免疫危险理论的信号机制,提出了多形态检测算法,该算法使用二进制形态和实值形态两种检测器协同检测,通过协同信号判定事件是否异常。经实验表明,该多形态检测算法较单一形态检测算法在检测性能上有了极大的提高。To solve immunity-based intrusion detection systems＇ lower detection performence caused by their detectors＇ shape kinds of the binary and the real-valued, the defects of the two kinds of shape were analyzed, and a new multi- shape detection（MSD） algorithm was presented according to the idiotypic immune network theory and the signal mechanism in the immune danger theory. The MSD algorithm uses binary and real-valued detectors to monitor the events by collaborative signals. The experimental results show that the new detection algorithm can improve the de- tective performance of detectors.

关 键 词：免疫入侵检测 形态空间 二进制 实值 检测器 多形态 否定选择算法 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]