Local Differential Privacy Is Equivalent to Contraction of an $f$-Divergence

Shahab Asoodeh, Maryam Aliakbarpour, Flávio P. Calmon

Abstract

We investigate the local differential privacy (LDP) guarantees of a randomized privacy mechanism via its contraction properties. We first show that LDP constraints can be equivalently cast in terms of the contraction coefficient of the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathsf{E}_{\gamma}$</tex> -divergence. We then use this equivalent formula to express LDP guarantees of privacy mechanisms in terms of contraction coefficients of arbitrary <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$f$</tex> -divergences. When combined with standard estimation-theoretic tools (such as Le Cam's and Fano's converse methods), this result allows us to study the trade-off between privacy and utility in several testing and minimax and Bayesian estimation problems.
BibTeX
@inproceedings{asoodeh2021local,
  author = {Shahab Asoodeh and Maryam Aliakbarpour and Flávio P. Calmon},
  title = {{Local Differential Privacy Is Equivalent to Contraction of an $f$-Divergence}},
  booktitle = {ISIT},
  year = {2021},
  doi = {10.1109/isit45174.2021.9517999},
}
Figure