16 citations · 17 across the 15 of their papers we have counts for
7 papers · 1 filter
Practitioners' Perspectives on a Differential Privacy Deployment Registry
Priyanka Nanayakkara, Elena Ghazi, Salil Vadhan
Differential privacy (DP) -- a principled approach to producing statistical data products with strong, mathematically provable privacy guarantees for the individuals in the underly…
Securing Unbounded Differential Privacy Against Timing Attacks
Zachary Ratliff, Salil Vadhan
Recent works have started to theoretically investigate how we can protect differentially private programs against timing attacks, by making the joint distribution the output and th…
Characterizing the Distinguishability of Product Distributions through Multicalibration
Cassandra Marcussen, Aaron Putterman, Salil Vadhan
Given a sequence of samples promised to be drawn from one of two distributions , a well-studied problem in statistics is to decide dis…
A Framework for Differential Privacy Against Timing Attacks
Zachary Ratliff, Salil Vadhan
The standard definition of differential privacy (DP) ensures that a mechanism's output distribution on adjacent datasets is indistinguishable. However, real-world implementations o…
Programming Frameworks for Differential Privacy
Marco Gaboardi, Michael Hay, Salil Vadhan
Many programming frameworks have been introduced to support the development of differentially private software applications. In this chapter, we survey some of the conceptual ideas…
Membership Inference Attacks and Privacy in Topic Modeling
Nico Manzonelli, Wanrong Zhang, Salil Vadhan
Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, li…
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…