Skype encrypted traffic identification based on trend-aware protocol fingerprints
Wang We · Jisuanji yingyong yanjiu · 2015
The P2 P technology greatly facilitated resource sharing on the Internet.It held the largest proportion of network traffic and was usually encrypted,which led to the problem of bandwidth consumption and lack of supervision.Accurate and rapid detection of encrypted P2 P traffic,represented by the famous Skype,was of great significance to improve the network quality of service and enhance security controls.This paper proposed a trend-aware protocol fingerprints model based on the statistical characteristics of signaling interactions and content transfer phase of Skype.The proposed method could sense traffic trends by trend-aware weighting functions and identify Skype traffic with anomaly scores in real time.Experimental results show that the precision and real-time performances of the proposed algorithm is better than several state-of-art encrypted traffic detection methods,such as the protocol fingerprints and C4.5 algorithm.