异常检测系统的漏洞分析

来源期刊:中南大学学报(自然科学版)2009年第4期

论文作者:刘星宝 蔡自兴

文章页码:986 - 992

关键词:人工免疫系统;阴性选择算法;漏洞;异常检测

Key words:artificial immune systems; negative selection algorithm; hole; anomaly detection

摘    要:针对阴性选择算法生成的异常检测系统存在大量漏洞的问题,提出一种能够探测系统全部漏洞的非检测模式漏洞探测算法(EHANDP)。首先,指出目前检测系统漏洞探测算法(EHASP)的不完备性;然后,利用问题空间中的串模式证明空间中个体成为漏洞的充分必要条件,并提出探测系统漏洞的完备性算法EHANDP,能够找出给定系统的全部漏洞是该算法的主要特点。实验中采用随机数据集和人工数据集比较2种漏洞探测算法。研究结果表明:在相同的实验环境下,EHANDP算法与EHASP相比不仅有相同的计算复杂度,而且有更强的探测能力。

Abstract: A novel exploring holes algorithm based on non-detector pattern (EHANDP) was proposed for holes existing in anomaly detection system generated by negative selection algorithm. Incompleteness of current exploring holes algorithm grounded on self pattern (EHASP) was pointed out. And then the sufficient and necessary condition for individuals to become holes was proven using the string patterns in problem space, and an exploring holes algorithm named EHANDP which could find all holes of a given detection system was proposed. The above two algorithms were compared using random dataset and artificial dataset. The results show that the exploring capability of EHANDP algorithm is greater than that of EHASP although they have the same computational complexity.

基金信息:国家自然科学基金资助项目
国家基础研究项目
国家博士点基金资助项目

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号