A network intrusion detection approach combined with genetic algorithm and back propagation neural network

Abstract

IDS can offer protection from external users and internal attackers, where traffic doesn't go past the firewall at all. The research on IDS attempted to use neural networks for intrusion detection has been carried on and will continue. Such systems were trained on normal or attack behavior information and then detect intrusions or attacks. In this paper, we have described five kinds of Neural Network technologies that are used in IDS. An IDS combining with GA and BP is put forward, and functions of each module are detailed. Finally, a discussion of the future NN technologies, which promise to enhance the detection ability of IDS is provided.