Differentially Private Query Release Through Adaptive Projection

Abstract

We propose, implement, and evaluate a new algorithm for releasing answers to very large numbers of statistical queries like $k$-way marginals, subject to differential privacy. Our algorithm makes adaptive use of a continuous relaxation of the Projection Mechanism, which answers queries on the private dataset using simple perturbation, and then attempts to find the synthetic dataset that most closely matches the noisy answers. We use a continuous relaxation of the synthetic dataset domain which makes the projection loss differentiable, and allows us to use efficient ML optimization techniques and tooling. Rather than answering all queries up front, we make judicious use of our privacy budget by iteratively and adaptively finding queries for which our (relaxed) synthetic data has high error, and then repeating the projection. We perform extensive experimental evaluations across a range of parameters and datasets, and find that our method outperforms existing algorithms in many cases, especially when the privacy budget is small or the query class is large.

References in corpus (7)

• From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
• A simple and practical algorithm for differentially private data release
• Optimizing error of high-dimensional statistical queries under differential privacy
• Graphical-model based estimation and inference for differential privacy
• Private Post-GAN Boosting
• Oracle Efficient Private Non-Convex Optimization
• P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model

Cited by in corpus (5)

• How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
• Confidence-Ranked Reconstruction of Census Microdata from Published Statistics
• Synthetic Tabular Data: Methods, Attacks and Defenses
• Turbo: Effective Caching in Differentially-Private Databases
• Differentially Private Synthetic Data Release for Topics API Outputs