基于阴性选择算法的异常检测系统黑洞覆盖优化  

Anomaly detection system with hole coverage optimization based on negative selection algorithm

作　　者：芦天亮[1] 郑康锋[1] 傅蓉蓉[2] 杨义先[1] 武斌[1] 郭世泽[1] 

机构地区：[1]北京邮电大学信息安全中心,北京100876 [2]北京交通大学计算机科学与技术系,北京100044

出　　处：《通信学报》2013年第1期128-135,共8页Journal on Communications

基　　金：国家科技重大专项课题基金资助项目(2011ZX03002-005-01);国家自然科学基金资助项目(61101108)~~

摘　　要：针对阴性选择算法存在大量无法检测的黑洞,提出了一种基于黑洞集合和自我集合定向生成匹配阈值可变的r块黑洞检测器的算法。对阴性选择算法进行改进,提出了采用双重检测器的阴性选择算法DLD-NSA,该算法在保证较快的检测速度的前提下,通过提高黑洞元素检测率,实现更大范围的非我空间覆盖。仿真结果表明,该算法与变长r连续位阴性选择算法相比,具有更高的非我空间覆盖率,尤其是在黑洞覆盖方面效果更好。With the problem that a large number of undetectable holes existed in negative selection algorithm, an algo-rithm of directional generating holes＇ detectors using r-chunk matching rule with variable matching threshold based on hole-set and self-set was proposed. Improvement was made to negative selection algorithm that NSA with double layers detectors was proposed. This algorithm achieved a wider range of non-self space coverage with the precondition of en- suring fast detection speed by increasing the detection rate of holes. Simulation result shows that comparing with NSA using variable matching length of r-contiguous bits this algorithm can achieve higher non-self space coverage, especially better performance in hole-space coverage.

关 键 词：人工免疫系统 阴性选择算法 黑洞 r连续位 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]