Deakin University
Browse

File(s) under permanent embargo

Traffic identification in big internet data

Version 2 2024-06-06, 00:28
Version 1 2016-08-08, 16:31
chapter
posted on 2024-06-06, 00:28 authored by B Wang, J Zhang, Zili ZhangZili Zhang, Wei LuoWei Luo, D Xia
The era of big data brings new challenges to the network traffic technique that is an essential tool for network management and security. To deal with the problems of dynamic ports and encrypted payload in traditional port-based and payload-basedmethods, the state-of-the-art method employs flow statistical features and machine learning techniques to identify network traffic. This chapter reviews the statistical-feature based traffic classification methods, that have been proposed in the last decade. We also examine a new problem: unclean traffic in the training stage of machine learning due to the labeling mistake and complex composition of big Internet data. This chapter further evaluates the performance of typical machine learning algorithms with unclean training data. The review and the empirical study can provide a guide for academia and practitioners in choosing proper traffic classification methods in real-world scenarios.

History

Chapter number

3

Pagination

129-156

ISBN-13

9783319277639

Language

eng

Publication classification

B Book chapter, B1 Book chapter

Copyright notice

2016, Springer International Publishing Switzerland

Extent

12

Editor/Contributor(s)

Yu S, Guo S

Publisher

Springer

Place of publication

Berlin, Germany

Title of book

Big data concepts, theories, and applications