Internet traffic classiffication is an essential task for manag-ing large networks. Network design, routing optimization, quality of service management, anomaly and intrusion de-tection tasks can be improved with a good knowledge of the traffic. Traditional classiffication methods based on transport port analysis have become inappropriate for modern applications.

nbsp, Payload based analysis using pattern searching have privacy concerns and are usually slow and expensive in computa-tional cost. In recent years, traffic classiffication based on the statistical properties of

nbsp,flows has become a relevant topic. In this work we analyze the size of the firsts packets on both directions of a flow as a relevant statistical finngerprint. This finngerprint is enough for accurate traffic classiffcation and so can be useful for early traffic identification in real time.

nbsp, This work proposes the use of a supervised machine learning clustering method for traffic classiffcation based on Support Vector Machines. We compare our method accuracy with a more classical centroid based approach, obtaining promising results.

nbsp,