2 citations · 3 across the 5 of their papers we have counts for
5 papers
"I inherently just trust that it works": Investigating Mental Models of Open-Source Libraries for Differential Privacy
Patrick Song, Jayshree Sarathy, Michael Shoemate +1
Differential privacy (DP) is a promising framework for privacy-preserving data science, but recent studies have exposed challenges in bringing this theoretical framework for privac…
Private Means and the Curious Incident of the Free Lunch
Jack Fitzsimons, James Honaker, Michael Shoemate +1
We show that the most well-known and fundamental building blocks of DP implementations -- sum, mean, count (and many other linear queries) -- can be released with substantially red…
Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters
Samuel Haney, Michael Shoemate, Grace Tian +4
In this paper, we study the concurrent composition of interactive mechanisms with adaptively chosen privacy-loss parameters. In this setting, the adversary can interleave queries t…
Sotto Voce: Federated Speech Recognition with Differential Privacy Guarantees
Michael Shoemate, Kevin Jett, Ethan Cowan +3
Speech data is expensive to collect, and incredibly sensitive to its sources. It is often the case that organizations independently collect small datasets for their own use, but of…
Widespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix It
Sílvia Casacuberta, Michael Shoemate, Salil Vadhan +1
We identify a new class of vulnerabilities in implementations of differential privacy. Specifically, they arise when computing basic statistics such as sums, thanks to discrepancie…