Abnormal Traffic Classification based on Feature Entropy Vector

DOI

10.2991/mecae-17.2017.18How to use a DOI?

Keywords

Information Entropy, Feature Vector, Anomaly Detection, Classification.

Abstract

Existing anomaly detection technology is mainly concerned with the detection of anomalous flow, and it is not enough to study anomaly type. Therefore, a method based on information entropy and k-means clustering is proposed to construct the anomalous traffic entropy feature vector to achieve fast and accurate judgment of anomaly types. The method is simple and easy to operate. Simulation results show that the proposed method is effective in classifying and determining the common types of network attack anomalies.

Copyright

© 2017, 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  - Lulu Chen
AU  - Wenpu Guo
AU  - Hao He
PY  - 2017/03
DA  - 2017/03
TI  - Abnormal Traffic Classification based on Feature Entropy Vector
BT  - Proceedings of the 2017 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2017)
PB  - Atlantis Press
SP  - 101
EP  - 107
SN  - 2352-5401
UR  - https://doi.org/10.2991/mecae-17.2017.18
DO  - 10.2991/mecae-17.2017.18
ID  - Chen2017/03
ER  -