Abstract
Abstract: In this talk we will describe two current and recent deployments of DP at the US Census Bureau and the IRS that Tumult Labs is involved with. We will describe the data products and some of the considerations taken into account when designing DP algorithms for these deployments. We will also highlight our methodology of engaging with key stakeholders to iteratively elicit requirements for privacy and fitness-for-use as well as design and tune a differentially private algorithm that meets these requirements.
Bio: Ashwin Machanavajjhala is an Associate Professor in the Department of Computer Science, Duke University, and co-founder of Tumult Labs. His primary research interests lie in algorithms for privacy preserving data analytics with a focus on differential privacy. He is an ACM Distinguished Member, a recipient of the ACM SIGMOD 2021 Test of Time and IEEE ICDE 2017 Influential Paper awards, and the NSF Faculty Early CAREER award in 2013. In collaboration with the US Census Bureau, he is credited with developing the first real world deployment of differential privacy. Ashwin graduated with a Ph.D. from the Department of Computer Science, Cornell University and a B.Tech in Computer Science and Engineering from the Indian Institute of Technology, Madras.