Integral Privacy for Sampling

TL;DR

This paper introduces a novel approach to integral privacy in sampling, enabling strong group privacy guarantees without sensitivity scaling, and demonstrates its effectiveness through theoretical analysis and experimental validation.

Contribution

It proposes a new sampling method that achieves integral privacy without sensitivity analysis, using boosting and classifiers to approximate non-private densities.

Findings

Achieves privacy guarantees close to the information theoretic barrier.

Provides approximation guarantees for mode capture in density estimation.

Demonstrates superior performance compared to private kernel density estimation and private GANs.

Abstract

Differential privacy is a leading protection setting, focused by design on individual privacy. Many applications, in medical / pharmaceutical domains or social networks, rather posit privacy at a group level, a setting we call integral privacy. We aim for the strongest form of privacy: the group size is in particular not known in advance. We study a problem with related applications in domains cited above that have recently met with substantial recent press: sampling. Keeping correct utility levels in such a strong model of statistical indistinguishability looks difficult to be achieved with the usual differential privacy toolbox because it would typically scale in the worst case the sensitivity by the sample size and so the noise variance by up to its square. We introduce a trick specific to sampling that bypasses the sensitivity analysis. Privacy enforces an information theoretic barrier on approximation, and we show how to reach this barrier with guarantees on the approximation of the target non private density. We do so using a recent approach to non private density estimation relying on the original boosting theory, learning the sufficient statistics of an exponential family with classifiers. Approximation guarantees cover the mode capture problem. In the context of learning, the sampling problem is particularly important: because integral privacy enjoys the same closure under post-processing as differential privacy does, any algorithm using integrally privacy sampled data would result in an output equally integrally private. We also show that this brings fairness guarantees on post-processing that would eventually elude classical differential privacy: any decision process has bounded data-dependent bias when the data is integrally privately sampled. Experimental results against private kernel density estimation and private GANs displays the quality of our results.