Study on intrusion detection model based on improved genetic algorithm and fuzzy neural network

Abstract

The network intrusion is one of the most important issues for the security of the internet. The internet intrusion may lead to terrible disaster for network users. It is therefore imperative to detect the network attacks to protect the information security. However, the intrusion detection rate is often affected by the structure parameters of the fuzzy neural network (FNN). Improper FNN model design may result in a low detection precision. To overcome these problems, a new network intrusion detection approach based on improved genetic algorithm (GA) and FNN is proposed in this chapter. The improved GA used energy entropy to select individuals to optimize the training procedure of the FNN, and satisfactory FNN model with proper structure parameters was then attained. The efficiency of the proposed method was evaluated with the practical data. The experiment results show that the proposed approach offers a good intrusion detection rate, and performs better than the standard GA-FNN method with respect to the detection rate. Thus, the proposed new intrusion detection method is efficient for practice applications. © 2012 Springer Science+Business Media B.V.