We show how to achieve differential privacy with no or reduced added noise, based on the empirical noise in the data itself. Unlike previous works on noiseless privacy, the empirical viewpoint avoids making any explicit assumptions about the random process generating the data.
@article{arxiv.1910.12820,
title = {Empirical Differential Privacy},
author = {Paul Burchard and Anthony Daoud and Dominic Dotterrer},
journal= {arXiv preprint arXiv:1910.12820},
year = {2023}
}