A Novel Features Set for Internet Traffic Classification using Burstiness

Hussein Oudah, Bogdan Ghita, Taimur Bakhshi

2019

Abstract

Traffic classification is an essential tool for network management and security. Traditional techniques such as port-based and payload analysis are ineffective as major Internet applications use dynamic port numbers and encryption. Recent studies have used statistical properties of flows to classify traffic with high accuracy, minimising the overhead limitations associated with other schemes such as deep packet inspection (DPI). Classification accuracy of statistical flow-based approaches, however, depends on the discrimination ability of the traffic features used. To this effect, the present paper customised the popular tcptrace utility to generate classification features based on traffic burstiness and periods of inactivity (idle time) for everyday Internet usage. An attempt was made to train a C5.0 decision tree classifier using the proposed features for eleven different Internet applications, generated by ten users. Overall, the newly proposed features reported a significant level of accuracy (~98%) in classifying the respective applications.

Paper Citation

in Harvard Style

Oudah H., Ghita B. and Bakhshi T. (2019). A Novel Features Set for Internet Traffic Classification using Burstiness.In Proceedings of the 5th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP, ISBN 978-989-758-359-9, pages 397-404. DOI: 10.5220/0007384203970404

in Bibtex Style

@conference{icissp19,
author={Hussein Oudah and Bogdan Ghita and Taimur Bakhshi},
title={A Novel Features Set for Internet Traffic Classification using Burstiness},
booktitle={Proceedings of the 5th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,},
year={2019},
pages={397-404},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007384203970404},
isbn={978-989-758-359-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,
TI - A Novel Features Set for Internet Traffic Classification using Burstiness
SN - 978-989-758-359-9
AU - Oudah H.
AU - Ghita B.
AU - Bakhshi T.
PY - 2019
SP - 397
EP - 404
DO - 10.5220/0007384203970404