中文摘要：

生物免疫系统是一个高度进化的生物系统，它能够智能区分和抵抗外部有害抗原，产生抗体，清除病原，保持机体稳定．仿照生物免疫系统，研究者们提出了人工免疫系统（artificial immune system，AIS）．基于类比推理的免疫模型的核心是把类比推理方法应用于人工免疫系统的克隆选择和否定选择过程．该模型把遗传算法与AIS相结合，对初始异常行为样本集合进行优化，并从异常性和正常性两方面考虑，提出了网络行为异常概率算法、在此基础上建立了一种网络入侵检测系统模型．

英文摘要：

Nature immune system is a highly developed biology system. It can intelligently recognize, resist and clear the foreign maleficent antigen by generating antibody. Therefore, this system keeps stable biology environment. Following the nature immune system researchers have raised the theory of AIS, i.e. Artificial Immune System. The analogy-based immune model focuses on the implementation of the clone selection process and the negative selection process by means of analogy-based reasoning. Firstly, the initial abnormal behaviours sample set is optimized by combining the AIS and the genetic algorithm. Then, the abnormity probability algorithm is raised considering the two sides of abnormality and normality. Finally, an intrusion detection system model is established based on the above algorithms and models.