基于免疫算法和神经网络的新型抗体网络  

A Novel Antibody Network Base on Immune Algorithm and Neural Network

作　　者：陈科[1] 许家珆[1] 程永新[1] 

机构地区：[1]电子科技大学应用数学学院,成都610054

出　　处：《电子科技大学学报》2006年第5期804-806,840,共4页Journal of University of Electronic Science and Technology of China

基　　金：四川省科技厅基础项目(04JY029-017-1)

摘　　要：构建了基于免疫算法和神经网络的新型抗体网络入侵检测系统,系统与网络入侵检测功能相结合,应用于大型网络的入侵检测任务,具有良好的可扩充性;重点讨论了新型抗体网络原理,引进BP神经网络自学习能力,对已有的抗体网络模型进行改进;通过对网络数据集的测试表明,该算法相对于传统抗体网络,其检测效率得到了明显的改善。This paper designs an antibody network （ABNET） based on immune algorithm and neural network used for Intrusion Detection System. The ABNET system combines network-based intrusion detection functions. It can be used to protect large area network and has relatively good expansibility. This paper also discusses the theory of the ABNET. The algorithm has been tested on a network data set. The result shows that it had much better performance than traditional ABNET.

关 键 词：入侵检测算法 免疫算法 神经网络 抗体网络 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]