人工免疫中匹配算法研究

针对现有基于人工免疫理论入侵检测系统中的亲和力匹配算法研究的不足,导致检测结果误报率和漏报率较高的问题,提出了一种新的进化匹配机制.定义了自体非自体,给出了成熟细胞动态方程,亲和力累积方程和进化匹配算法,建立了模型的形式化描述.采用动态匹配算法加快了进化速度,保存了具有优势特征的物种,提高了检测效率和准确性,使得对抗原的识别率更为有效.实验结果表明,该模型具有定量、高效率和较好的准确性,能积极主动的保护系统不受实质性攻击.为构建新一代高效合理的网络安全系统提供了一种有效方案.

Matching Algorithm in Artificial Immune System

Aiming at the deficiencies of current matching algorithm based on AIS (Artificial immune system), such as fault positive is high and the efficiency is very low, an improved evolution optimization with r-continuous bits matching rule was proposed. The concepts and formal definitions of immune cells were given, affinity accumulation process, and mature-lymphocyte lifecycle were presented. This new algorithm introduces evolution operator into the matching rule during the affinity accumulation process to improve the detection efficiency and overcome the shortcoming of the local optimum. Experimental results showed that the algorithm greatly enhances the response rate and the precision of detection, and the proposed model has the features of real-time processing, self-adaptively, thus providing a promising solution for intrusion detection.