Proceedings of the 2018 3rd International Conference on Communications, Information Management and Network Security (CIMNS 2018)

A Lightweight Traffic Anomaly Detection Model in SDN Based on Decision Tree

Authors
Dong Li, Zizhun Li
Corresponding Author
Dong Li
Available Online November 2018.
DOI
10.2991/cimns-18.2018.8How to use a DOI?
Keywords
SDN; network security; anomaly detection
Abstract

This paper establishes a SDN-based network traffic anomaly detection model based on decision tree. Firstly, five statistical indexes are presented to describe the behavior of network traffic, then normal and abnormal traffic data to train the machine learning model to detect traffic anomaly. Four machine learning algorithms, decision tree, k-nearest neighbor, support vector machine and naive Bayes, are used to predict the detection rate, false alarm rate and other indicators. Experiments shows that decision tree algorithm is suitable for detecting traffic anomaly in SDN network.

Copyright
© 2018, 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)

Volume Title
Proceedings of the 2018 3rd International Conference on Communications, Information Management and Network Security (CIMNS 2018)
Series
Advances in Computer Science Research
Publication Date
November 2018
ISBN
978-94-6252-620-4
ISSN
2352-538X
DOI
10.2991/cimns-18.2018.8How to use a DOI?
Copyright
© 2018, 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/).

Cite this article

TY  - CONF
AU  - Dong Li
AU  - Zizhun Li
PY  - 2018/11
DA  - 2018/11
TI  - A Lightweight Traffic Anomaly Detection Model in SDN Based on Decision Tree
BT  - Proceedings of the 2018 3rd International Conference on Communications, Information Management and Network Security (CIMNS 2018)
PB  - Atlantis Press
SP  - 35
EP  - 39
SN  - 2352-538X
UR  - https://doi.org/10.2991/cimns-18.2018.8
DO  - 10.2991/cimns-18.2018.8
ID  - Li2018/11
ER  -