SYBILFUSE: Combining local attributes with global structure to perform robust sybil detection

Sybil attacks are becoming increasingly widespread and pose a significant threat to online social systems; a single adversary can inject multiple colluding identities in the system to compromise security and privacy. Recent works have leveraged social network-based trust relationships to defend against Sybil attacks. However, existing defenses are based on oversimplified assumptions about network structure, which do not necessarily hold in real-world social networks. Recognizing these limitations, we propose SYBILFUSE, a defense-in-depth framework for Sybil detection when the oversimplified assumptions are relaxed. SYBILFUSE adopts a collective classification approach by first training local classifiers to compute local trust scores for nodes and edges, and then propagating the local scores through the global network structure via weighted random walk and loopy belief propagation mechanisms. We evaluate our framework on both synthetic and real-world network topologies, including a large-scale, labeled Twitter network comprising 20M nodes and 265M edges, and demonstrate that SYBILFUSE outperforms state-of-the-art approaches significantly. In particular, SYBILFUSE achieves 98% of Sybil coverage among top-ranked nodes.