ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy

arXiv:2308.12210v3 Announce Type: replace-cross
Abstract: Differentially Private Federated Learning (DP-FL) has garnered attention as a collaborative machine learning approach that ensures formal privacy. Most DP-FL approaches ensure DP at the record-level within each silo for cross-silo FL. However, a single user's data may extend across multiple silos, and the desired user-level DP guarantee for such a setting remains unknown. In this study, we present Uldp-FL, a novel FL framework designed to guarantee user-level DP in cross-silo FL where a single …

arxiv attention cs.cr cs.lg data differential privacy federated federated learning machine machine learning may privacy private record silos single the record