Michael Hay, Tumult Labs and Colgate University
This talk will present Tumult Analytics, a soon-to-be-open-source platform for SQL-like analytics with configurable differential privacy guarantees. It is currently used by a variety of organizations -- including the US Census Bureau, US Internal Revenue Service, and Wikimedia -- to publicly share aggregate statistics about populations of interest. The platform’s design emphasizes usability, especially for data scientists who may be new to differential privacy, but also scalability and expressivity so that it can power production use cases that produce 100s millions of statistics with tight privacy accounting. The platform is supported by multi-layer architecture consisting of a user-friendly dataframe-like interface on top of an extensible privacy framework on top of Apache Spark. This talk will describe the platform with a focus on usability features that help programmers write deployable DP programs safely and quickly.
Michael Hay, Tumult Labs and Colgate University
Michael Hay is the Founder/CTO of Tumult Labs, a startup that helps organizations safely release data using differential privacy, and an Associate Professor of Computer Science at Colgate University. He was previously a Research Data Scientist at the US Census Bureau and a Computing Innovation Fellow at Cornell University. He holds a Ph.D. from the University of Massachusetts Amherst and a bachelor's degree from Dartmouth College.
author = {Michael Hay},
title = {Designing an {Open-Source} Platform for Differentially Private Analytics That Is Usable, Scalable, and Extensible},
year = {2022},
address = {Santa Clara, CA},
publisher = {USENIX Association},
month = jun
}
