Robust traffic classification with mislabelled training samples

Wang, Binfeng, Zhang, Jun, Zhang, Zili, Luo, Wei and Xia, Dawen 2015, Robust traffic classification with mislabelled training samples, in ICPADS 2015: Proceedings of the IEEE Parallel and Distributed Systems 2015 International Conference, IEEE, Piscataway, N. J., pp. 328-335, doi: 10.1109/ICPADS.2015.49.

Attached Files
Name Description MIMEType Size Downloads

Title Robust traffic classification with mislabelled training samples
Author(s) Wang, Binfeng
Zhang, JunORCID iD for Zhang, Jun
Zhang, ZiliORCID iD for Zhang, Zili
Luo, WeiORCID iD for Luo, Wei
Xia, Dawen
Conference name IEEE Parallel and Distributed Systems. International Conference (21st : 2015 : Melbourne, Vic.)
Conference location Melbourne, Vic.
Conference dates 14-17 Dec. 2015
Title of proceedings ICPADS 2015: Proceedings of the IEEE Parallel and Distributed Systems 2015 International Conference
Editor(s) [Unknown]
Publication date 2015
Conference series IEEE Parallel and Distributed Systems International Conference
Start page 328
End page 335
Total pages 8
Publisher IEEE
Place of publication Piscataway, N. J.
Keyword(s) traffic classification
unclean internet data
machine learning
random forest
network security
Summary Traffic classification plays the significant role in the network security and management. However, accurate classification is challenging if the training data is contaminated with unclean traffic. Recent researches often assume clean training data, and hence performance reduced on real-time network traffic. To meet this challenge, in this paper, we propose a robust method, Unclean Traffic Classification (UTC), which incorporates noise elimination and suspected noise reweighting. Firstly, UTC eliminates strong noisy training data identified by a consensus filtering with multiple classifiers. Furthermore, UTC estimates the relevance of remaining training data and learns a robust traffic classifier. Through a number of experiments on a real-world traffic dataset, we show that the new method outperforms existing state-of-the-art traffic classification methods, under the extremely difficult circumstance with unclean training data.
ISBN 9780769557854
ISSN 1521-9097
Language eng
DOI 10.1109/ICPADS.2015.49
Field of Research 010204 Dynamical Systems in Applications
Socio Economic Objective 890205 Information Processing Services (incl. Data Entry and Capture)
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2015, IEEE
Persistent URL

Connect to link resolver
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 2 times in TR Web of Science
Scopus Citation Count Cited 3 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 308 Abstract Views, 4 File Downloads  -  Detailed Statistics
Created: Fri, 01 Jul 2016, 17:48:29 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact