Social Turing Tests: Crowdsourcing Sybil Detection
Download: Paper (PDF)
Date: 23 Apr 2013
Document Type: Presentations
Additional Documents: Slides
Associated Event: NDSS Symposium 2013
We explore the feasibility of a crowdsourced system using human intuition to detect Sybil (fake accounts) in online social networks. We conduct a large user study using a large corpus of ground-truth from Facebook and Renren, and users from Amazon Turk and Chinese crowdsourcing systems. We find this approach promising and propose a multi-tier detection system that is both scalable and highly accurate.