A Wavelet Kernel-Based Support Vector Machine for Communication Network Intrusion Detection

Abstract

This study is to propose a wavelet kernel-based support vector machine for communication network intrusion detection. The common intrusion types of communication network mainly include DOS, R2L, U2R and Probing. Support vector machine, BP neural network are used to compare with the proposed wavelet kernel-based support vector machine method to show the superiority of wavelet kernel-based support vector machine. The detection accuracy for communication network intrusion of wavelet kernel-based support vector machine is 96.67 %, the detection accuracy for communication network intrusion of support vector machine is 90.83%, and the detection accuracy for communication network intrusion of BP neural network is 86.67%. It can be seen that the detection accuracy for communication network intrusion of wavelet kernel-based support vector machine is better than that of support vector machine or BP neural network.