一种用于入侵检测的改进人工免疫算法

Improved Artificial Immune Algorithm Used in Intrusion Detection

通过对基于信息熵和基于欧氏距离的免疫算法的分析和改进,提出一种新的适用于入侵检测的人工免疫算法(AIAID)。该算法引入马氏距离的思想,改进相似度和期望繁殖率的计算,把抗体不同特征的重要性和取值范围加入到相关运算中,对算法流程进行优化。设计一种新的基于AIAID的入侵检测系统模型。实验表明,将AIAID用于入侵检测能够明显缩短训练时间,提高检测效率。

By analyzing and improving the artificial immune algorithm based on information entropy and Euclidean distance, a novel Artificial Immune Algorithm based on intrusion Detection（AIAID） is proposed. The algorithm lies on improving the calculation about similarity and expected breed rate by the principle of Mahalanobis distance, namely introducing the importance and value range of antibody characteristics into correlation computing, and algorithm flow is optimized. A new model for intrusion detection system is designed by using AIAID. Tests indicate that using AIAID in intrusion detection can obviously shorten training time and improve detection efficiency.