Pictures from the Skype Dario Rossi, Silvio Valenti, Paolo Veglia TELECOM ParisTech, France Dario Bon glio, Marco Mellia, Michela Meo Politecnico di Torino, Italy rst.last@enst.fr rst.last@polito.it ABSTRACT This paper focuses on the characterization and classi cation of Skype traf c, a nowadays very popular and fashionable VoIP application. Building over previous work, we develop a software tool which can be used to examine the evolution of Skype call classi cation in an interactive fashion. The demonstrator software focuses on the main aspects of Skype traf c characterization and presents the traf c patterns Skype generates during a call or while idle. In addition, the demonstrator shows the evolution of the internal indexes the Skype classi ers use. After describing the classi cation process and the demonstrator software, we use the tool to demonstrate the feasibility of online Skype traf c identi cation, considering both accuracy and computational costs. Experimental results show that few seconds of observation are enough to allow the classi er engines to correctly identify the presence of Skype ows. Moreover, results indicate that the classi cation engine can cope with multi-Gbps links in real-time using common off-the-shelf hardware. Categories and Subject Descriptors C.4 [Computer Communication]:
/lp/association-for-computing-machinery/pictures-from-the-skype-tFrkQsJuXE