Radial Basic Function-Based Intrusion Detection Systems
基于径向基函数的入侵检测系统

An intrusion detection system is a critical component for secure information management, and an intrusion detection system is an art to detect network intrusions by monitoring the network traffic patterns. In this paper, radial basic functions neural network was introduced into intrusion detection system and a network intrusion detection system based on radial basic functions neural network (RBFIDS) was designed. The system first gathers information of the network, then uses K-means clustering methods to determine the parameters of RBF neural network. The experiments were run on the KDD-99 datasets for performance evaluation, the system achieved a correct detection rate equal to 98% and a false detection rate equal to 1.6%. The experimental results show the RBFIDS system improves the performance of intrusion detection systems with a high detecting rate and a low false positive.