Differentially Private Bayesian Programming

  title={Differentially Private Bayesian Programming},
  author={Gilles Barthe and Gian Pietro Farina and Marco Gaboardi and Emilio Jes{\'u}s Gallego Arias and Andrew D. Gordon and Justin Hsu and Pierre-Yves Strub},
  booktitle={ACM Conference on Computer and Communications Security},
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… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 10 times over the past 90 days. VIEW TWEETS


Publications citing this paper.
Showing 1-10 of 11 extracted citations


Publications referenced by this paper.
Showing 1-8 of 8 references

The algorithmic foundations of differential privacy

  • C. Dwork, A. Roth
  • Foundations and Trends in Theoretical Computer…
  • 2014
Highly Influential
5 Excerpts

Robust bayesian analysis using divergence measures

  • D. K. Dey, L. R. Birmiwal
  • Statistics & Probability Letters,
  • 1994
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…