General inferential limits under differential and Pufferfish privacy

• Published in: International journal of approximate reasoning Vol. 172; p. 109242
• Main Authors: Bailie, James, Gong, Ruobin
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.09.2024
• Subjects: Bayesian inference; Density bounded class; Density ratio neighbourhood; Distortion model; Interval of measures; Lipschitz continuity; Multiplicative distance; Neyman-Pearson hypothesis testing; Prior-to-posterior-semantics; Statistical disclosure control; Statistical disclosure control; Distortion model; Multiplicative distance; Neyman-Pearson hypothesis testing; Interval of measures; Prior-to-posterior-semantics; Density bounded class; Density ratio neighbourhood; Bayesian inference; Lipschitz continuity

Differential privacy (DP) is a class of mathematical standards for assessing the privacy provided by a data-release mechanism. This work concerns two important flavors of DP that are related yet conceptually distinct: pure ε-differential privacy (ε-DP) and Pufferfish privacy. We restate ε-DP and Puf...