PeerMate: a malicious peer detection algorithm for P2P systems based on MSPCA

Many reputation management schemes have been introduced to assist peers to choose the most trustworthy collaborators in P2P environment where honest peers coexist with malicious ones. These schemes indeed provide some useful information about the reliability of peers, but still suffer from various attacks including slandering, collusion and so on. Consequently, how to detect malicious peers plays a critical role in successful work of these mechanisms, and it will also be our focus in this paper. Firstly, we divide the malicious peers into six categories; secondly, we bring forward PeerMate, a malicious peers detection algorithm based on Multiscale Principal Component Analysis (MSPCA) and Quality of Reconstruction (QR), to detect malicious peers in reputation based P2P systems; finally, we show through simulations that PeerMate can detect malicious peers efficiently and accurately