16 citations · 65 across the 9 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CR2022★ 8 cited
Tumult Analytics: a robust, easy-to-use, scalable, and expressive framework for differential privacy
Skye Berghel, Philip Bohannon, Damien Desfontaines +10
In this short paper, we outline the design of Tumult Analytics, a Python framework for differential privacy used at institutions such as the U.S. Census Bureau, the Wikimedia Found…
cs.CR2022★ 7 cited
Precision-based attacks and interval refining: how to break, then fix, differential privacy on finite computers
Samuel Haney, Damien Desfontaines, Luke Hartman +2
Despite being raised as a problem over ten years ago, the imprecision of floating point arithmetic continues to cause privacy failures in the implementations of differentially priv…