Google 2021 Paper
Title: Clustering for Private Interest-based Advertising
Authors: Alessandro Epasto (Google), Andrés Muñoz Medina (Google), Steven Avery (Google), Yijian Bai (Google), Róbert István Busa-Fekete (Google), Cj Carey (Google), Ya Gao (Google), David Guthrie (Google), Subham Ghosh (Google), James Ioannidis (Google), Junyi Jiao (Google), Jakub Ła̧cki (Google), Jason Lee (Google), Arne Mauser (Google), Brian Milch (Google),Vahab Seyed Mirrokni (Google), Deepak Ravichandran (Google), Wei Shi (Google), Max Spero (Google), Yunting Sun (Google), Umar Syed (Google), Sergei Vassilvitskii (Google), Shuo Wang (Google)
Abstract/Summary: We study the problem of designing privacy-enhanced solutions for interest-based advertisement (IBA). IBA is a key component of the online ads ecosystem and provides a better ad experience to users. Indeed, IBA enables advertisers to show users impressions that are relevant to them. Nevertheless, the current way ad tech companies achieve this is by building detailed interest profiles for individual users. In this work we ask whether such fine grained personalization is required, and present mechanisms that achieve competitive performance while giving privacy guarantees to the end users. More precisely we present the first detailed exploration of how to implement Chrome’s Federated Learning of Cohorts (FLoC) API. We define the privacy properties required for the API and evaluate multiple hashing and clustering algorithms discussing the trade-offs between utility, privacy, and ease of implementation.