Containing sybil attacks on trust management schemes for peer-to-peer networks

In this paper, we introduce a framework to detect possible sybil attacks against a trust management scheme of peer-to-peer (P2P) networks used for limiting the proliferation of malware. Sybil attacks may underscore the effectivity of such schemes as malicious peers may use bogus identities to artificially manipulate the reputation, and therefore, the levels of trust of several legitimate and honest peers. The framework includes a k-means clustering scheme, a method to verify the transactions reported by peers, and identification of possible collaborations between peers. We prove that as the amount of public information on peers increases, the effectivity of sybil attacks may decrease. We study the performance of each of these mechanisms, in terms of the number of infected peers in a P2P network, using computer simulation. We show the effect of each mechanism and their combinations. We show that the combination of these schemes is effective and efficient.