Title :

On the Differential Privacy of Bayesian Inference

Author(s) :

Zhang, Zuhe [Auteur correspondant]
University of Melbourne
Rubinstein, Benjamin [Auteur]
University of Melbourne
Dimitrakakis, Christos [Auteur]
Université de Lille, Sciences Humaines et Sociales
Sequential Learning [SEQUEL]

Conference title :

AAAI 2016 - Thirtieth AAAI Conference on Artificial Intelligence

City :

Phoenix, Arizona

Country :

Etats-Unis d'Amérique

Start date of the conference :

2016-02-10

Publication date :

2015-02-12

English keyword(s) :

Bayesian inference
posterior sampling
differential privacy

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Cryptographie et sécurité [cs.CR]
Mathématiques [math]/Statistiques [math.ST]
Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Machine Learning [stat.ML]
Économie et finance quantitative [q-fin]/Econométrie de la finance [q-fin.ST]
Sciences de l'Homme et Société/Economies et finances

English abstract : [en]

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 ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL