Network Intrusion Detection Based on PSO-SVM

Changsheng Xiang (Hunan Institute of Engineering)
Yong Xiao (Hunan Agricultural University)
Peixin Qu (Henan Institute of Science and Technology)
Xilong Qu (Hunan Institute of Engineering)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 12, No 2: February 2014

In order to improve network intrusion detection precision, this paper proposed a network intrusion detection model based on simultaneous selecting features and parameters of support vector machine (SVM) by particle swarm optimization (PSO) algorithm. Firstly, the features and parameters of SVM are coded to particle, and then the PSO is used to find the  optimal features and SVM parameters by collaboration among particles, lastly, the performance of the model was tested by KDD Cup 99 data. Compared with other network models, the proposed model has reduced input features for SVM and has significantly improved the detection precision of network intrusion. DOI : http://dx.doi.org/10.11591/telkomnika.v12i2.3826