基于神经网络的协同入侵检测  

A Cooperative Intrusion Detection System Based on BP Neural Network

作　　者：杜红乐[1] 

机构地区：[1]商洛学院计算机科学系,陕西商洛726000

出　　处：《商洛学院学报》2011年第2期54-58,共5页Journal of Shangluo University

摘　　要：针对计算机网络规模大、网络流量大、结构复杂等特点,使得检测代理负载过大导致丢包率较高而准确率较低,提出了基于神经网络的协同入侵检测,该方法根据网络协议构建多个检测代理(TCP检测代理、UDP检测代理和ICMP检测代理),多个检测代理协同工作减少检测代理的负载,从而提高检测准确率。最后用KDDCUP99进行仿真实验,结果表明该方法可以有效提高训练时间和检测时间,同时提高准确率。Problems of high-speed networks,large traffic flow and complex topology in current computer networks lead to detection agent＇s high packet loss rate and low detection accuracy because of its excessive load.This paper proposes a cooperative intrusion detection based on BP Neural network. According to Network protocol,construct multiple detection agents（TCP detection agent,UDP detection agent and ICMP detection agent）.Reduce the detection agent load and improve detection accuracy by using Multi-agents cooperative work.Finally,make experiment with KDDCUP99 dataset,and experimental results show that the method proposed in this paper not only reduce the training time and testing time but also improve the detection accuracy.

关 键 词：网络安全 神经网络 入侵检测 协同 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]