A Cooperative Intrusion Detection System Based on BP Neural Network
Hongle Du · Journal of Shangluo University · 2011
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.