Achieving Pareto-Optimal MI-Based Privacy-Utility Tradeoffs Under Full Data.

We study a fine-grained model in which a perturbed version of some data (D) is to be disclosed, with the aims of permitting the receiver to accurately infer some useful aspects (X = f(D)) of it, while preventing her from inferring other private aspects (Y = g(D)). Correlation between the bases for these inferences necessitates compromise between these goals. Determining exactly how the disclosure ...