5:00-6:00 pm, Seminar Hall
Towards Catching Click-Spam on Facebook Ads
Users are increasingly influenced by liked posts and ads on Facebook. This has led to a market for black-hat promotion techniques via fake (e.g., Sybil) and compromised accounts, and collusion networks. We present a study of click-spam on Facebook, investigate sources of click-spam traffic, and design techniques to identify such clicks with high confidence. Our technique works with no apriori labeling while maintaining low false-positive rates. Using ground-truth data from Facebook ads, we find our technique identifies click-spam better than existing approaches.
Saikat Guha is a researcher at Microsoft Research India. He is broadly interested in systems approaches to improving privacy and security in online advertising. His recent projects are focused on online social networks, and mobile ecosystems. Saikat received his PhD from Cornell University in 2009. He authored the RFC that now serves as the best-practice for building TCP support in NATs and firewalls. He received his BS in computer science from Cornell University in 2003. In 2012, he was named one of MIT Technology Review's TR-35 (35 young innovators under 35).