论文信息 - A Preliminary Investigation of Skype Traffic Classification Using a Minimalist Feature Set

A Preliminary Investigation of Skype Traffic Classification Using a Minimalist Feature Set

In this work, AdaBoost and C4.5, are employed for classifying Skype direct (UDP and TCP) communications from traffic log files. Pre-processing is applied to the traffic data to express it as flows, which is later converted into a descriptive feature set. The aforementioned algorithms are then evaluated on this feature set. Results show that a 98% detection rate with 6% false positive rate for UDP based Skype and a 94% detection rate with 4% false positive rate for TCP based Skype is possible to achieve.

A. Nur Zincir-Heywood | Duffy Angevine | A. N. Zincir-Heywood | D. Angevine

[1] Charles V. Wright,et al. HMM profiles for network traffic classification , 2004, VizSEC/DMSEC '04.

[2] Sebastian Zander,et al. Evaluating machine learning algorithms for automated network application identification , 2006 .

[3] Andrew W. Moore,et al. Internet traffic classification using bayesian analysis techniques , 2005, SIGMETRICS '05.

[4] Michalis Faloutsos,et al. BLINC: multilevel traffic classification in the dark , 2005, SIGCOMM '05.

[5] Patrick Haffner,et al. ACAS: automated construction of application signatures , 2005, MineNet '05.

[6] Simson L. Garfinkel. VoIP and Skype Security , 2005 .

[7] Anirban Mahanti,et al. Traffic classification using clustering algorithms , 2006, MineNet '06.

[8] Henning Schulzrinne,et al. An Analysis of the Skype Peer-to-Peer Internet Telephony Protocol , 2004, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[9] Renata Teixeira,et al. Traffic classification on the fly , 2006, CCRV.

[10] Konstantina Papagiannaki,et al. Toward the Accurate Identification of Network Applications , 2005, PAM.

[11] P. Biondi,et al. Silver Needle in the Skype , 2006 .