基于模糊规则与免疫演化的报警关联方法  

Alert Correlation Approach Based on Fuzzy Rule and Immunity Evolution

作　　者：汪永伟[1,2] 赵荣彩[1] 张红旗[1,2] 刘育楠[1,2] 

机构地区：[1]信息工程大学,河南郑州450001 [2]河南省信息安全重点实验室,河南郑州450001

出　　处：《信息工程大学学报》2015年第3期370-377,共8页Journal of Information Engineering University

基　　金：国家973计划资助项目(2011CB311801);国家863计划资助项目(2012AA012704)

摘　　要：针对现有基于人工免疫的关联分析方法在亲和力计算中的问题,提出了一种基于模糊规则与人工免疫的关联分析方法。该方法首先采用粗糙集理论对注入的疫苗和抗体结构进行优化,并对特征属性进行重要性评价,然后通过加权欧几里德距离度量特征向量与抗体的亲和力,以提高亲和力计算的效果与关联分析的精度。实验仿真结果表明,该方法在完备率和有效率等方面优于现有典型关联分析方法。According to the problem of affinity in alert correlation analysis based on artificial immu- nity, a new alert correlation approach based on fuzzy rule and immunity evolution is proposed. First, the vaccine and the antibody are optimized based on the rough set, and the importance of feature at- tributes is evaluated. Then, the affinity between feature and antibody is measured based on the weighted Euclidean distance to improve the effect of affinity calculation and the accuracy of correla- tion analysis. The results of experiments show that the new approach is superior to typical approa- ches in completeness and effectiveness.

关 键 词：关联分析 人工免疫 亲和力 粗糙集 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]