Leveraging Public Data for Practical Private Query Release
This addresses the challenge of improving privacy-preserving data analysis for applications like census statistics, though it is incremental by building on existing methods with public data.
The paper tackled the problem of differentially private query release by incorporating prior knowledge from public datasets, resulting in a method that outperforms state-of-the-art approaches and scales well to high-dimensional data.
In many statistical problems, incorporating priors can significantly improve performance. However, the use of prior knowledge in differentially private query release has remained underexplored, despite such priors commonly being available in the form of public datasets, such as previous US Census releases. With the goal of releasing statistics about a private dataset, we present PMW^Pub, which -- unlike existing baselines -- leverages public data drawn from a related distribution as prior information. We provide a theoretical analysis and an empirical evaluation on the American Community Survey (ACS) and ADULT datasets, which shows that our method outperforms state-of-the-art methods. Furthermore, PMW^Pub scales well to high-dimensional data domains, where running many existing methods would be computationally infeasible.