Pain-Free Random Differential Privacy with Sensitivity Sampling

DOI10.48550/ARXIV.1706.02562MaRDI QIDQ153660arXivFDO

Authors Benjamin I. P. Rubinstein, Francesco Aldà

Publication date 8 June 2017

Abstract: Popular approaches to differential privacy, such as the Laplace and exponential mechanisms, calibrate randomised smoothing through global sensitivity of the target non-private function. Bounding such sensitivity is often a prohibitively complex analytic calculation. As an alternative, we propose a straightforward sampler for estimating sensitivity of non-private mechanisms. Since our sensitivity estimates hold with high probability, any mechanism that would be $(epsilon,delta)$-differentially private under bounded global sensitivity automatically achieves $(epsilon,delta,gamma)$-random differential privacy (Hall et al., 2012), without any target-specific calculations required. We demonstrate on worked example learners how our usable approach adopts a naturally-relaxed privacy guarantee, while achieving more accurate releases even for non-private functions that are black-box computer programs.

Cited in

(1)

• diffpriv

This page was built for publication: Pain-Free Random Differential Privacy with Sensitivity Sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q153660)