Network Intrusion Detection Based on the Improved Artificial Fish Swarm Algorithm

Abstract

In order to predict network anomalies and get rid of the drawbacks of current detection, early prediction of abnormal for detecting early characteristics of the abnormal is introduced in the invasion anomaly detection process. First, the objective functions are constructed according to the feature subset dimensions and the detection accurate rates of the detection model. Then the artificial fish swarm algorithm is used to search the optimal feature subset and the chaotic, feedback mechanisms are introduced to improve the artificial fish swarm algorithm, the excessive intrusion feature rough sets produced in the classification process are simplified to guarantee the simplicity of characteristics and the estimation model for residuals gray level to predicate the early simplified invasion. Finally KDD1999 database is applied to testify the validity of the algorithm. The simulation results illustrate the improved artificial fish swarm algorithm can obtain the optimal intrusion feature subsets and reduce the dimensions of the feature subsets, which not only increase the network intrusion detection rates and reduce the errors, but also speed up the network abnormal intrusion detection.