On the Differential Privacy of Bayesian Inference

Zuhe Zhang 1, * Benjamin Rubinstein 1 Christos Dimitrakakis 2, 3, 4
* Auteur correspondant
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : We study how to communicate findings of Bayesian inference to third parties, while preserving the strong guarantee of differential privacy. Our main contributions are four different algorithms for private Bayesian inference on proba-bilistic graphical models. These include two mechanisms for adding noise to the Bayesian updates, either directly to the posterior parameters, or to their Fourier transform so as to preserve update consistency. We also utilise a recently introduced posterior sampling mechanism, for which we prove bounds for the specific but general case of discrete Bayesian networks; and we introduce a maximum-a-posteriori private mechanism. Our analysis includes utility and privacy bounds, with a novel focus on the influence of graph structure on privacy. Worked examples and experiments with Bayesian naïve Bayes and Bayesian linear regression illustrate the application of our mechanisms.
Liste complète des métadonnées

https://hal.inria.fr/hal-01234215
Contributeur : Zuhe Zhang <>
Soumis le : lundi 20 février 2017 - 22:16:03
Dernière modification le : jeudi 12 avril 2018 - 11:14:04
Document(s) archivé(s) le : dimanche 21 mai 2017 - 12:13:06

Fichier

HAL.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01234215, version 2
  • ARXIV : 1512.06992

Citation

Zuhe Zhang, Benjamin Rubinstein, Christos Dimitrakakis. On the Differential Privacy of Bayesian Inference. AAAI 2016 - Thirtieth AAAI Conference on Artificial Intelligence, Feb 2016, Phoenix, Arizona, United States. 2015. 〈hal-01234215v2〉

Partager

Métriques

Consultations de la notice

413

Téléchargements de fichiers

138