Traffic classification on the fly

Laurent Bernaille (1) , Renata Teixeira (1) , Ismael Akodjenou (1) , Augustin Soule (2) , Kavé Salamatian (1)

1 NPA - Networks and Performance Analysis
2 Technicolor R & I [Cesson Sévigné]

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 ap-plication 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 ap-plication. This result opens a range of new possibilities for online traffic classification.

Mots clés: Traffic classification; Applications; Machine Learning

Domaines: Réseaux et télécommunications [cs.NI]

Laurent Bernaille, Renata Teixeira, Ismael Akodjenou, Augustin Soule, Kavé Salamatian. Traffic classification on the fly. Computer Communication Review, 2006, 36 (2), pp.23-26. ⟨10.1145/1129582.1129589⟩. ⟨hal-01097551⟩