A P2P Protocol Identification Algorithm Based on PSO-SVM

Abstract

The growing of P2P applications enriched the resources sharing by network, but it also brought many problems such as occupying network bandwidth, security of personal information. Therefore, the monitor of P2P applications is very important, and P2P protocol identification is the key point. So far since the P2P appeared, new P2P applications and data encryption made the traditional port-based and application layer protocol signature recognition useless. To overcome the shortcomings of current methods, a new P2P identification algorithm is proposed which uses DFI (Deep Flow Inspection) by extracting the various properties of P2P data stream characteristics, and then the data flows are divided into TCP and UDP data sets, finally the support vector machine optimized by particle swarm optimization is used to assort the network data streams, Experimental results of the P2P and non-P2P applications show that this algorithm can identify the HTTP applications 100% and for a variety of P2P applications, the accuracy of classification can also reach to 95%.