Soft computing approach based malicious peers detection using geometric and trust features in P2P networks

The attacks in P2P networks can be classified into two types: passive and active attacks. Passive attacks refer to the attempts made by malicious nodes to perceive the activities, whereas the active attacks are attacks performed by the malicious nodes that bear some energy cost to perform the attack. Malicious peer detection in P2P networks is a complication task due to the similar characteristics between trusty peer and malicious peer. This paper focuses the malicious peer detection system using feed forward back propagation neural networks. The characteristic features such as Geometric and Trust features are extracted from the peers in P2P networks and these extracted features are trained and classified using neural networks. The performance of the proposed malicious peer detection system is analyzed in terms of latency and detection rate.