Privacy: A few definitional aspects and consequences for minimax mean-squared error
Rina Foygel Barber, John C. Duchi · 2014
We explore several definitions of “privacy” in statistical estimation and data analysis. We present and review definitions that attempt to capture what, intuitively, it should mean to limit disclosures from the output of a statistical estimation task, providing minimax upper and lower bounds on mean squared error for estimation problems under several common (and some new) definitions of privacy.