Differential Privacy for Bayesian Inference through Posterior Sampling

Abstract : Differential privacy formalises privacy-preserving mechanisms that provide access to a database. Can Bayesian inference be used directly to provide private access to data? The answer is yes: under certain conditions on the prior, sampling from the posterior distribution can lead to a desired level of privacy and utility. For a uniform treatment, we define differential privacy over arbitrary data set metrics, outcome spaces and distribution families. This allows us to also deal with non-i.i.d or non-tabular data sets. We then prove bounds on the sensitivity of the posterior to the data, which delivers a measure of robustness. We also show how to use posterior sampling to provide differentially private responses to queries, within a decision-theoretic framework. Finally, we provide bounds on the utility of answers to queries and on the ability of an adversary to distinguish between data sets. The latter are complemented by a novel use of Le Cam's method to obtain lower bounds on distinguishability. Our results hold for arbitrary metrics, including those for the common definition of differential privacy. For specific choices of the metric, we give a number of examples satisfying our assumptions. *. A preliminary version of this paper appeared in Algorithmic Learning Theory 2014 (Dimitrakakis et al., 2014). This version corrects proofs, constant factors in the upper bounds and introduces new material on utility analysis, lower bounds and examples.
Type de document :
Article dans une revue
Journal of Machine Learning Research, Journal of Machine Learning Research, 2017, 18 (11), pp.1−39
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01500302
Contributeur : Christos Dimitrakakis <>
Soumis le : lundi 3 avril 2017 - 07:35:50
Dernière modification le : mardi 3 juillet 2018 - 11:38:43
Document(s) archivé(s) le : mardi 4 juillet 2017 - 12:20:17

Fichier

15-257.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01500302, version 1

Citation

Christos Dimitrakakis, Blaine Nelson, Zuhe Zhang, Aikateirni Mitrokotsa, Benjamin Rubinstein. Differential Privacy for Bayesian Inference through Posterior Sampling. Journal of Machine Learning Research, Journal of Machine Learning Research, 2017, 18 (11), pp.1−39. 〈hal-01500302〉

Partager

Métriques

Consultations de la notice

443

Téléchargements de fichiers

123