Impact of peer incentives on the dissemination of polluted content

Recent studies have reported a new form of malicious behav-ior in ¯le-sharing Peer-to-Peer systems: content pollution. The dissemination of polluted content in a P2P system has the detrimental e®ect of reducing content availability, and ultimately, decreasing the con¯dence of users in such sys-tems. Two potential strategies for polluting P2P content are decoy insertion, which consists of injecting corrupted copies of a ¯le into the system, and hash corruption, which consists of injecting a corrupted ¯le with the same hash code as a non-corrupted one. Polluted content disseminates through P2P networks because users typically do not delete the cor-rupted ¯les that they download. This paper investigates the e®ectiveness of peer incentives to delete corrupted ¯les in reducing the dissemination of pol-luted content, considering the two aforementioned pollution mechanisms. Our simulation results show that the e®ec-tiveness of incentives is highly dependent on the pollution mechanism. We show that for a pollution dissemintation techinique called hash corruption, only e®ective incentive mechanisms are able to avoid spreading of polluted content