Private Federated Statistics in an Interactive Setting
Audra McMillan, Omid Javidbakht, Kunal Talwar, Elliot Briggs, Mike Chatzidakis, Junye Chen, John C. Duchi, Vitaly Feldman, Yusuf Gören, M. Hesse, Vojta Jina, Anil Katti, Albert Liu, Cheney Lyford, Joey Meyer, Alex Palmer, David S. Park, Won-Hee Park, Gianni Parsa, Paul Pelzl · arXiv (Cornell University) · 2022
Privately learning statistics of events on devices can enable improved user experience. Differentially private algorithms for such problems can benefit significantly from interactivity. We argue that an aggregation protocol can enable an interactive private federated statistics system where user's devices maintain control of the privacy assurance. We describe the architecture of such a system, and analyze its security properties.