Off-line analysis of internet traffic for accurate identification of P2P applications using neural networks

P2P applications supposedly constitute a substantial proportion of today´s Internet traffic. The ability to accurately identify different P2P applications in internet traffic is important to a broad range of network operations including application-specific traffic engineering, capacity planning, resource provisioning, service differentiation, etc. However, current P2P applications use several obfuscation techniques, including dynamic port numbers, port hopping, and encrypted payloads. As P2P applications continue to evolve, robust and effective methods are needed for identification of P2P applications. In this paper, we compare two neural network approaches (Radial Basis Function Network and Multi-Layer Perceptron) that precisely identify the P2P traffic. We find out that RBFN outperforms MLP neural network, but owing to the large time taken for model building, RBF network is found suitable for off-line identification of P2P applications in the internet traffic.