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

Ying Zhan

doi:10.4028/www.scientific.net/AMR.989-994.4474

Paper Titles

Three Networks Convergence Analysis Based on SWOT Theory
p.4456

The Research of Multi-Network Switching Model for Power Communication Network Based on Analytic Hierarchy Process
p.4461

Active Online Thematic Map Cartography Based on Network
p.4466

Study on One Generating Method of Digital Painting Patterns
p.4470

A Wavelet Kernel-Based Support Vector Machine for Communication Network Intrusion Detection
p.4474

The Attendance Management System Based on Micro-Cellular and GIS Technology
p.4478

A Prevention Scheme for Black Hole Attack Based on NS2
p.4482

Design and Implementation of a Software Automation Development Framework for Management Information System
p.4488

Study on the Adaptive Congestion Control Algorithms for Wireless Sensor Networks
p.4493

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 989-994A Wavelet Kernel-Based Support Vector Machine for...

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 (SVM) for communication network intrusion detection. The common intrusion types of communication network mainly include DOS, R2L, U2R and Probing. SVM, BP neural network are used to compare with the proposed wavelet kernel-based SVM method to show the superiority of wavelet kernel-based SVM. The detection accuracy for communication network intrusion of wavelet kernel-based SVM is 96.67 %, the detection accuracy for communication network intrusion of SVM 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 SVM is better than that of SVM or BP neural network.