差分隐私的统计视角：假设检验、表示与布莱克威尔定理
A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem
AI总结：
本文从统计视角重新解读差分隐私，基于Blackwell定理证明其所有定义可从假设检验视角推导，提出f-差分隐私统一框架并分析其在多领域应用中的优势，论证假设检验是推理差分隐私的恰当语言。
摘要：
差分隐私因具备稳健且严格的保障，被广泛视为隐私保护数据分析的正式隐私标准，在公共服务、学术界和工业界的应用日益广泛。尽管起源于密码学语境，但本综述论文认为，从根本上讲，差分隐私可被视为一个纯粹的统计概念。通过利用David Blackwell的信息性定理，我们基于已有工作证明：所有差分隐私定义都能从假设检验视角得到正式动机，这表明假设检验不仅方便，更是推理差分隐私的恰当语言。这一洞见引出了f-差分隐私的定义，该定义通过表示定理扩展了其他差分隐私定义。我们回顾了使f-差分隐私成为数据分析和机器学习中隐私边界分析统一框架的技术。还讨论了该差分隐私定义在私有深度学习、私有凸优化、洗牌机制和美国人口普查数据中的应用，以突出相比现有替代方案，在该框架下分析隐私边界的优势。
英文摘要：
Differential privacy is widely considered the formal privacy for privacy-preserving data analysis due to its robust and rigorous guarantees, with increasingly broad adoption in public services, academia, and industry. Despite originating in the cryptographic context, in this review paper we argue that, fundamentally, differential privacy can be considered a \textit{pure} statistical concept. By leveraging David Blackwell's informativeness theorem, our focus is to demonstrate based on prior work that all definitions of differential privacy can be formally motivated from a hypothesis testing perspective, thereby showing that hypothesis testing is not merely convenient but also the right language for reasoning about differential privacy. This insight leads to the definition of $f$-differential privacy, which extends other differential privacy definitions through a representation theorem. We review techniques that render $f$-differential privacy a unified framework for analyzing privacy bounds in data analysis and machine learning. Applications of this differential privacy definition to private deep learning, private convex optimization, shuffled mechanisms, and U.S.\ Census data are discussed to highlight the benefits of analyzing privacy bounds under this framework compared to existing alternatives.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
