Behavior-based P2P traffic identification using fuzzy approach

The use of P2P applications has been in rise over past several years due to their capabilities to share large volumes of files, efficiently transport large amounts of voice and video, allow anonymous browsing etc. bypassing the controls enforced by the service providers. Therefore the detection of these applications has become a challenge for ISPs and network administrators. In this paper, we propose P2P host identification framework based on fuzzy pattern recognition. The fuzzy patterns are examined from the behavior of P2P and NonP2P flows. We define several membership functions based on the behavioral characteristics including: (1) Bytes per second, (2) Packet Inter Arrival Time, (3) Packet count per second and (4) Number of unique hosts contacted. The performance evaluation based on the real-time traces show that the proposed system promises more than 98% of accuracy and a low false positive rate of ≈2%.