基于小生境策略的否定選擇算法利用在搜索空間中計(jì)算檢測(cè)器之間的海明距離，構(gòu)建小生境；定義適應(yīng)度函數(shù)與親合力函數(shù)相關(guān)，更客觀地反映檢測(cè)器的檢測(cè)能力；利用進(jìn)化策略，進(jìn)行遺傳操作，而生成多樣性和通用性的最佳檢測(cè)器集。同時(shí)該算法可以減少生成檢測(cè)器的時(shí)間開(kāi)銷(xiāo)。
關(guān)鍵詞 小生境；否定選擇；檢測(cè)器；匹配規(guī)則；網(wǎng)絡(luò)入侵檢測(cè)
Algorithm Research for Generating Diversity Detectors Zhang Hong1 , Cai Huan fu1 , Gao Ping an2 （1. Department of Computer Science and Technolgy , Guangdong University of Finance, Guangzhou 510521, China; 2. School of Information Science and Engineering Central South University, Changsha 410083, China） Abstract A negative selection algorithm with niching strategy can generate diversity and generality of detector sets. By calculating Hamming distance between two arbitrary detectors insearch space, niching of detectors is built. A new approach to define the fitness function is proposed. The fitness function is a relational function of the detector’s affinity function. And computational time can be reduced.
Keywords niching, negative selection, detectors, match rule, network intrusion detection