摘要
目前入侵检测中传统否定选择算法忽略了正常和异常模式之间的模糊界限而造成了检测效率低下,以及生成的检测器数量冗繁,用在非我模式识别时计算复杂度相当高。针对这些缺陷,重点研究了在入侵检测系统中定义模糊检测规则的重要性,并提出利用免疫算法的优化搜索性能来进化模糊检测器的方法。实验结果表明,该方法生成的检测器能够允许更简洁的自我和非我的表示方式,降低了检测规则的脆弱性,检测效果较好。
The neglect of the fuzzy limit between the self and nonselfgave the poor efficiency of detection, where traditional negative selection algorithm is used in intrusion detection. And the computational complexity by using large numbers of detectors is too high. Aimed at these flaws, the necessary of fuzzy detection rules, and a hybrid approach are proposed which uses the searching performance of immune algorithm to generate fuzzy-detectors. The results ofthe experirnent prove that fuzzy rules express the self/nonselfs compactly, reduce the fi-angibility of detectors greatly and have an exciting feature.
出处
《计算机工程与设计》
CSCD
北大核心
2008年第10期2496-2498,共3页
Computer Engineering and Design
关键词
入侵检测
模糊界限
免疫算法
优化搜索
模糊检测器
脆弱性
intrusion detection
fuzzy limit
immune algorithm
optimization search
fuzzy detector
frangibility