基于人工免疫的网络入侵检测模型的研究  

Research of Network Intrusion Detection Model Based on Artificial Immune

作　　者：张玉芳[1] 熊忠阳[1,2] 孙桂华[1] 赖苏[1] 赵鹰[1] 

机构地区：[1]重庆大学计算机学院,重庆400030 [2]重庆大学信息与网络管理中心,重庆430030

出　　处：《计算机科学》2009年第12期108-110,共3页Computer Science

摘　　要：针对现有的应用于网络入侵检测中的人工免疫系统存在的缺陷,在Kim小组的动态克隆选择算法的基础上,提出了改进的网络入侵检测模型。在该模型中,提出产生少量的自体模式类对正常访问数据进行处理,加快其访问速度;通过动态增减自体集合来适应网络环境的变化,并且解决传统AIS中自体集合庞大的问题;采用基于约束的检测器表示抗体,采取任意R位间隔匹配规则来判定抗体与抗原之间的匹配,使用分割算法来解决抗体与自体抗原的匹配情况。最后,对该模型进行了网络入侵检测仿真实验,并与相同实验条件下的动态克隆选择算法的实验结果进行了对比,验证了所提模型的有效性和可行性。Aiming at limitation of existent network intrusion detection model with artificial immune idea, an improved network intrusion detection model based on dynamic clonal selection algorithm was presented. For accelerating normal IP packets access, the self-pattern class was proposed and most of self-antigens were filtered and amended the self-antigen set dynamically in detection process. The constraint-based detectors were adopted as antibody, any-r intervals matching rule was used to determinant antibody and antigen, and split-detector method were settled to self-antigen matching. The experimental results show that the proposed model can achieve a faster running speed, the better detecting rates, and adapt to dynamically changing environments.

关 键 词：入侵检测 人工免疫 抗体 抗原 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]