Traffic classification on the fly

The early detection of applications associated with TCP flows is an essential step for network security and traffic engineering. The classic way to identify flows, i.e. looking at port numbers, is not effective anymore. On the other hand, state-of-the-art techniques cannot determine the application before the end of the TCP flow. In this editorial, we propose a technique that relies on the observation of the first five packets of a TCP connection to identify the application. This result opens a range of new possibilities for online traffic classification. Categories and Subject Descriptors I.2.6 [Learning]: Unsupervised Learning; C.2.3 [Network Monitoring]: Network Management General Terms Measurement, Algorithms, Management Keywords Traffic classification, Applications, Machine Learning

• Type: Journal
• Year: 2006
• Where: CCR
• Authors: Laurent Bernaille, Renata Teixeira, Ismael Akodkenou, Augustin Soule, Kavé Salamatian
• Keywords: CCR 2006, Online Traffic Classification, TCP Flow, Traffic Classification