Fighting pollution dissemination in peer-to-peer networks

Abstract

Recent studies reported a new form of malicious behavior in popular file-sharing Peer-to-Peer (P2P) systems, namely, content pollution, which reduces content availability, decreasing the confidence of users in such systems. This paper proposes Scrubber, a new descentralized peer reputation system that imposes severe and quick punishment to content polluters but also promotes peer rehabilitation. We evaluate the efficiency of Scrubber in reducing pollution dissemination via simulation, comparing it against the previously proposed Credence object reputation system as well as a system without reputation. Two pollution mechanisms, namely, decoy insertion and identifier corruption, are considered. Our results show that, for various scenarios, Scrubber is able to quickly reduce the fraction of daily downloads to polluted content to a small percentage. If compared to Credence, Scrubber has a much better convergence and competitive maximum efficiency, unless the fraction of peers that delete their polluted content in response to punishment (i.e., download request refusals) is very small (under 25%). In this case, Credence achieves a slightly higher efficiency in the long run.