Private Sampling: A Noiseless Approach for Generating Differentially Private Synthetic Data
Year: 2022
Type: article
Abstract: In a world where artificial intelligence and data science become omnipresent, data sharing is increasingly locking horns with data-privacy concerns. Differential privacy has emerged as a rigorous framework for protecting individual privacy in a statistical database, while releasing useful statistical information about the database. The standard way to implement differential privacy is to inject a sufficient amount of noise into the data. However, in addition to other limitations of differential privacy, this process of adding noise will affect data accuracy and utility. Another approach to enable privacy in data sharing is based on the concept of synthetic data. The goal of synthetic data is to create an as-realistic-as-possible dataset, one that not only maintains the nuances of the original data, but does so without risk of exposing sensitive information. The combination of differential privacy with synthetic data has been suggested as a best-of-both-worlds solutions. In this work, we propose the first noisefree method to construct differentially private synthetic data; we do this through a mechanism called “private sampling.” Using the Boolean cube as benchmark data model, we derive explicit bounds on accuracy and privacy of the constructed synthetic data. The key mathematical tools are hypercontractivity, duality, and empirical processes. A core ingredient of our private sampling mechanism is a rigorous “marginal correction” method, which has the remarkable property that importance reweighting can be utilized to exactly match the marginals of the sample to the marginals of the population.
DOI: 10.1137/21m1449944
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
Funders: National Science Foundation, U.S. Army
Awards: ATD: A Mathematical Framework for Generating Synthetic Data, HDR TRIPODS: UC Davis TETRAPODS Institute of Data Science, ATD: Multimode Machine Learning and Deep GeoNetworks for Anomaly Detection, Operators on Banach Spaces, G5264306539, Collaborative Research: A Mathematical Framework for Generating Synthetic Data, High-Dimensional Probability for High-Dimensional Data
OpenAlex ID: W3202122949