D3p -- A Python Package for Differentially-Private Probabilistic Programming

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 $\sim$10 fold speed-up compared to an implementation using TensorFlow Privacy.

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Array Programming with NumPy
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Auto-Encoding Variational Bayes
• Deep Learning with Differential Privacy
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Pyro: Deep Universal Probabilistic Programming
• Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro
• Simple, Distributed, and Accelerated Probabilistic Programming
• The Discrete Gaussian for Differential Privacy
• The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
• Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization
• Randomness Concerns When Deploying Differential Privacy
• That which we call private
• Differentially Private Variational Inference for Non-conjugate Models
• Privacy-preserving data sharing via probabilistic modelling
• Computing Tight Differential Privacy Guarantees Using FFT
• Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT