Social turing tests: Crowdsourcing sybil detection

As popular tools for spreading spam and malware, Sybils (or fake accounts) pose a serious threat to online communi-ties such as Online Social Networks (OSNs). Today, sophis-ticated attackers are creating realistic Sybils that effectively befriend legitimate users, rendering most automated Sybil detection techniques ineffective. In this paper, we explore the feasibility of a crowdsourced Sybil detection system for OSNs. We conduct a large user study on the ability of hu-mans to detect today’s Sybil accounts, using a large cor-pus of ground-truth Sybil accounts from the Facebook and Renren networks. We analyze detection accuracy by both “experts ” and “turkers ” under a variety of conditions, and find that while turkers vary significantly in their effective-ness, experts consistently produce near-optimal results. We use these results to drive the design of a multi-tier crowd-sourcing Sybil detection system. Using our user study data, we show that this system is scalable, and can be highly ef-fective either as a standalone system or as a complementary technique to current tools.