Samplable Anonymous Aggregation for Private Federated Data Analysis
Kunal Talwar, Shan Wang, Audra McMillan, Vitaly Feldman, Pansy Bansal, Bailey Basile, Áine Cahill, Yi Sheng Chan, Michael Chatzidakis, Junye Chen, Oliver R. A. Chick, Mona Chitnis, Suman Ganta, Yusuf Gören, Filip Granqvist, Kristine Guo, F. J. Jacobs, Omid Javidbakht, Albert Liu, Richard Low · 2024
We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Locally differentially private algorithms require little trust but are (provably) limited in their utility. Centrally differentially private algorithms can allow significantly better utility but require a trusted curator. This gap has led to significant interest in the design and implementation of simple cryptographic primitives, that can allow central-like utility guarantees without having to trust a central server.