d3p - A Python Package for Differentially-Private Probabilistic Programming
Authors: Lukas Prediger (Aalto University, Finland.), Niki Loppi (NVIDIA AI Technology Center, Finland), Samuel Kaski (Aalto University, Finland & University of Manchester, UK), Antti Honkela (University of Helsinki, Finland 1 Available at: https://github.com/DPBayes/d3p)
Volume: 2022
Issue: 2
Pages: 407–425
DOI: https://doi.org/10.2478/popets-2022-0052
Abstract: We present d3p, a software package designed to help fielding runtime efficient widely-applicable Bayesian inference under differential privacy guarantees. d3p achieves general applicability to a wide range of probabilistic modelling problems by implementing the differentially private variational inference algorithm, allowing users to fit any parametric probabilistic model with a differentiable density function. d3p adopts the probabilistic programming paradigm as a powerful way for the user to flexibly define such models. We demonstrate the use of our software on a hierarchical logistic regression example, showing the expressiveness of the modelling approach as well as the ease of running the parameter inference. We also perform an empirical evaluation of the runtime of the private inference on a complex model and find a ∼10 fold speed-up compared to an implementation using TensorFlow Privacy.
Keywords: differential privacy, JAX, NumPyro, probabilistic programming, variational inference
Copyright in PoPETs articles are held by their authors. This article is published under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 license.
