Group Privacy Amplification and Unified Amplification by Subsampling for R\'enyi Differential Privacy

arXiv:2403.04867v1 Announce Type: cross
Abstract: Differential privacy (DP) has various desirable properties, such as robustness to post-processing, group privacy, and amplification by subsampling, which can be derived independently of each other. Our goal is to determine whether stronger privacy guarantees can be obtained by considering multiple of these properties jointly. To this end, we focus on the combination of group privacy and amplification by subsampling. To provide guarantees that are amenable to machine learning algorithms, we conduct our analysis in …

abstract arxiv cs.cr cs.lg differential differential privacy multiple post-processing privacy processing robustness stat.ml type