Robust network traffic identification with unknown applications

Zhang, Jun, Chen, Chao, Xiang, Yang, and Zhou, Wanlei (2013) Robust network traffic identification with unknown applications. In: Proceedings of the 8th ACM SIGSAC symposium on Information, Computer and Communications Security. pp. 405-414. From: ASIA CCS 2013: 8th ACM SIGSAC symposium on Information, Computer and Communications Security, 8-10 May 2013, Hanzhou, China.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website:


Traffic classification is a fundamental component in advancednetwork management and security. Recent research hasachieved certain success in the application of machine learn-ing techniques into flow statistical feature based approach.However, most of flow statistical feature based methods clas-sify traffic based on the assumption that all traffic flows aregenerated by the known applications. Considering the per-vasive unknown applications in the real world environment,this assumption does not hold. In this paper, we cast un-known applications as a specific classification problem withinsufficient negative training data and address it by propos-ing a binary classifier based framework. An iterative methodis proposed to extract unknown information from a set of un-labelled traffic flows, which combines asymmetric baggingand flow correlation to guarantee the purity of extractednegatives. A binary classifier is used as an application sig-nature which can operate on a bag of correlated flows insteadof individual flows to further improve its effectiveness. Wecarry out a series of experiments in a real-world network traf-fic dataset to evaluate the proposed methods. The resultsshow that the proposed method significantly outperformsthe-state-of-art traffic classification methods under the situ-ation of unknown applications present.

Item ID: 64411
Item Type: Conference Item (Research - E1)
ISBN: 978-1-4503-1767-2
Copyright Information: Copyright © 2013 by the Association for Computing Machinery,
Date Deposited: 11 Aug 2021 02:10
FoR Codes: 08 INFORMATION AND COMPUTING SCIENCES > 0803 Computer Software > 080303 Computer System Security @ 100%
SEO Codes: 89 INFORMATION AND COMMUNICATION SERVICES > 8902 Computer Software and Services > 890299 Computer Software and Services not elsewhere classified @ 100%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page