Visible to the public Differentially Private Bayesian Programming

TitleDifferentially Private Bayesian Programming
Publication TypeConference Paper
Year of Publication2016
AuthorsBarthe, Gilles, Farina, Gian Pietro, Gaboardi, Marco, Arias, Emilio Jesus Gallego, Gordon, Andy, Hsu, Justin, Strub, Pierre-Yves
Conference NameProceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security
PublisherACM
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-4139-4
KeywordsBayesian learning, Computing Theory, Differential privacy, Metrics, probabilistic programming, pubcrawl, security metrics, type systems
Abstract

We present PrivInfer, an expressive framework for writing and verifying differentially private Bayesian machine learning algorithms. Programs in PrivInfer are written in a rich functional probabilistic programming language with constructs for performing Bayesian inference. Then, differential privacy of programs is established using a relational refinement type system, in which refinements on probability types are indexed by a metric on distributions. Our framework leverages recent developments in Bayesian inference, probabilistic programming languages, and in relational refinement types. We demonstrate the expressiveness of PrivInfer by verifying privacy for several examples of private Bayesian inference.

URLhttp://doi.acm.org/10.1145/2976749.2978371
DOI10.1145/2976749.2978371
Citation Keybarthe_differentially_2016