Differentially private partition selection
Damien Desfontaines, James F. Voss, Bryant R. Gipson, Chinmoy V. Mandayam · DOAJ (DOAJ: Directory of Open Access Journals) · 2022
Many data analysis operations can be expressed as a GROUP BY query on an unbounded set of partitions, followed by a per-partition aggregation. To make such a query differentially private, adding noise to each aggregation is not enough: we also need to make sure that the set of partitions released is also differentially private.