Pufferfish Privacy: An Information-Theoretic Study

Abstract

Pufferfish privacy (PP) is a generalization of differential privacy (DP), that offers flexibility in specifying sensitive information and integrates domain knowledge into the privacy definition. Inspired by the illuminating formulation of DP in terms of mutual information due to Cuff and Yu, this work explores PP through the lens of information theory. We provide an information-theoretic formulation of PP, termed mutual information PP (MI PP), in terms of the conditional mutual information between the mechanism and the secret, given the public information. We show that MI PP is implied by the regular PP and characterize conditions under which the reverse implication is also true, recovering the relationship between DP and its information-theoretic variant as a special case. We establish convexity, composability, and post-processing properties for MI PP mechanisms and derive noise levels for the Gaussian and Laplace mechanisms. The obtained mechanisms are applicable under relaxed assumptions and provide improved noise levels in some regimes. Lastly, applications to auditing privacy frameworks, statistical inference tasks, and algorithm stability are explored.

References in corpus (9)

• Differential Privacy as a Mutual Information Constraint
• Auditing Differentially Private Machine Learning: How Private is Private SGD?
• Generalised Pinsker Inequalities
• Reviewing and Improving the Gaussian Mechanism for Differential Privacy
• Privacy-Utility Trade-off of Linear Regression under Random Projections and Additive Noise
• On Reverse Pinsker Inequalities
• Sliced Mutual Information: A Scalable Measure of Statistical Dependence
• k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension
• Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano

Cited by in corpus (4)

• Quantum Pufferfish Privacy: A Flexible Privacy Framework for Quantum Systems
• Contraction of Private Quantum Channels and Private Quantum Hypothesis Testing
• An invitation to the sample complexity of quantum hypothesis testing
• Measured Hockey-Stick Divergence and its Applications to Quantum Pufferfish Privacy