Persuasive Privacy

2026-01-30

AI Summary

This work addresses a critical limitation in existing privacy definitions, which often overlook purpose-driven requirements and struggle to accommodate deterministic algorithms. To overcome this, the authors propose a unified privacy quantification framework grounded in Bayesian game theory. This framework subsumes both pure and approximate differential privacy as special cases and, for the first time, provides formal privacy guarantees for deterministic algorithms. By explicitly modeling the adversary’s utility and posterior beliefs, the approach naturally yields a novel interpretation of post-processing invariance. The resulting framework not only encompasses mainstream privacy notions but also extends applicability to a broader class of algorithms, significantly enhancing both the theoretical expressiveness and practical relevance of formal privacy guarantees.

Technology Category

• Machine Learning: Privacy
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• Security and Privacy: Privacy-enhancing technologies
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

We propose a novel framework for measuring privacy from a Bayesian game-theoretic perspective. This framework enables the creation of new, purpose-driven privacy definitions that are rigorously justified, while also allowing for the assessment of existing privacy guarantees through game theory. We show that pure and probabilistic differential privacy are special cases of our framework, and provide new interpretations of the post-processing inequality in this setting. Further, we demonstrate that privacy guarantees can be established for deterministic algorithms, which are overlooked by current privacy standards.

Problem

• privacy
• Bayesian game theory
• differential privacy
• deterministic algorithms
• privacy guarantees

Innovation

• Bayesian game theory
• purpose-driven privacy
• differential privacy
• post-processing inequality
• deterministic algorithms