Total Variation Meets Differential Privacy
Abstract
The framework of approximate differential privacy is considered, and augmented by leveraging the notion of ``the total variation of a (privacy-preserving) mechanism'' (denoted by -TV). With this refinement, an exact composition result is derived, and shown to be significantly tighter than the optimal bounds for differential privacy (which do not consider the total variation). Furthermore, it is shown that -DP with -TV is closed under subsampling. The induced total variation of commonly used mechanisms are computed. Moreover, the notion of total variation of a mechanism is studied in the local privacy setting and privacy-utility tradeoffs are investigated. In particular, total variation distance and KL divergence are considered as utility functions and studied through the lens of contraction coefficients. Finally, the results are compared and connected to the locally differentially private setting.
Keywords
Cite
@article{arxiv.2311.01553,
title = {Total Variation Meets Differential Privacy},
author = {Elena Ghazi and Ibrahim Issa},
journal= {arXiv preprint arXiv:2311.01553},
year = {2024}
}
Comments
14 pages, 7 figures, partially published at 2023 IEEE ISIT and partially published at IEEE Journal on Selected Areas in Information Theory