A Novel Learning Algorithm on Probability Measure for Intrusion Detection

DOI

10.2991/cset-16.2016.31How to use a DOI?

Keywords

Intrusion detection, support vector machine, probability measures, kernal fuction

Abstract

Attacks cyber-based have already seriously threaten the security of network environment and network application with the rapid development and wide application of network services. Intrusion detection plays a vital role in the network security. The machine learning methods have been utilized in Intrusion Detection. Because the network intrusion system has to deal with a huge amount of data, its consumption is too large in the space and time. We present an algorithm that learns from probability measures instead of the specific samples in the traditional support vector machine (SVM).The novel algorithm can increase efficiency by the scale down dataset. The simulation test results on the KDD cup99 dataset show that our method is faster than traditional SVM algorithm at the premise of recognition accuracy.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiang Fang
AU  - Ying Jia
PY  - 2016/08
DA  - 2016/08
TI  - A Novel Learning Algorithm on Probability Measure for Intrusion Detection
BT  - Proceedings of the 2016 International Conference on Computer Science and Electronic Technology
PB  - Atlantis Press
SP  - 129
EP  - 132
SN  - 2352-538X
UR  - https://doi.org/10.2991/cset-16.2016.31
DO  - 10.2991/cset-16.2016.31
ID  - Fang2016/08
ER  -