3 papers
cs.LG2025
Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
Bogdan Kulynych, Juan Felipe Gomez, Georgios Kaissis +4
Differentially private (DP) mechanisms are difficult to interpret and calibrate because existing methods for mapping standard privacy parameters to concrete privacy risks -- re-ide…
cs.CY2025
Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
Alexandra Olteanu, Su Lin Blodgett, Agathe Balayn +7
In AI research and practice, rigor remains largely understood in terms of methodological rigor -- such as whether mathematical, statistical, or computational methods are correctly…
cs.CR2025
Debiasing Functions of Private Statistics in Postprocessing
Flavio Calmon, Elbert Du, Cynthia Dwork +2
Given a differentially private unbiased estimate of a statistic , we wish to obtain unbiased estimates of functions of , such as , solely th…