Artificial Neural Network Based Intrusion Detection Method Combined with Manifold Learning Algorithm
Computer and network security is one of the most emergency issues for a large scale of applications.The unexpected intrusion may make terrible disaster to the network users.It is therefore imperative to detect the network attacks to prevent this kind of violations.The intrusion patter recognition is now a hot topic in this research area.The use of the artificial neural networks (ANN) can provide intelligent intrusion detection.However,the intrusion detection rate is often affected by the input feature vector of the ANN.This is because the original feature space always contains a certain number of useless features.To overcome this problem,a new network intrusion detection approach based on manifold learning nonlinear feature dimension descending and ANN classifier is presented in this paper.The locally linear embedding (LLE) algorithm was used to reduce the original intrusion feature space.Then the satisfactory ANN model with proper input features was obtained.The efficiency of the proposed method was evaluated with the real intrusion data.The analysis results show that the proposed approach has good intrusion detection rate,and performs better than the standard GA-ANN method.
Intrusion detection Artificial neural network Locally linear embedding
Jinguang Chen Zhixiong Li
School of Teacher Education, Huzhou Teachers College, Huzhou, China School of Energy & Power Engineering, Wuhan University of Technology, China
国际会议
台湾
英文
3170-3174
2011-12-11（万方平台首次上网日期，不代表论文的发表时间）