Differential privacy has become the standard for private data analysis, and an extensive literature now offers differentially private solutions to a wide variety of problems. However, translating these solutions into practical systems often requires confronting details that the literature ignores or abstracts away: users may contribute multiple records, the domain of possible records may be unknown, and the eventual system must scale to large volumes of data. Failure to carefully account for all three issues can severely impair a system's quality and usability. We present Plume, a system built to address these problems. We describe a number of sometimes subtle implementation issues and offer practical solutions that, together, make an industrial-scale system for differentially private data analysis possible. Plume is currently deployed at Google and is routinely used to process datasets with trillions of records.
@article{arxiv.2201.11603,
title = {Plume: Differential Privacy at Scale},
author = {Kareem Amin and Jennifer Gillenwater and Matthew Joseph and Alex Kulesza and Sergei Vassilvitskii},
journal= {arXiv preprint arXiv:2201.11603},
year = {2022}
}