隐私核算ε经济学：通过后验界改进差分隐私组合
Privacy accounting $\varepsilon$conomics: Improving differential privacy composition via a posteriori bounds
AI总结：
本文提出输出差分隐私与新组合实验的后验隐私分析方法，在不削弱隐私保障的前提下优化DP组合的隐私-效用权衡，并验证了其在多种DP机制与场景中的适用性。
摘要：
差分隐私（Differential Privacy, DP）是发布聚合数据时用于隐私推理的广泛采用的概念。本文中，我们观察到某些DP机制适用于后验隐私分析，这类分析利用了部分输出泄露的输入数据库信息少于其他输出的特性。为利用这一现象，我们提出输出差分隐私（Output Differential Privacy, ODP）和一种新的组合实验，并借助这些新构造在组合场景下实现显著的隐私预算节省，优化隐私-效用权衡。这一切不会产生隐私成本，我们并未削弱隐私保障。\n为证明后验隐私分析技术的适用性，我们分析了两种知名机制：Sparse Vector Technique（稀疏向量技术）和Propose-Test-Release框架。随后我们展示了该技术如何在更通用的场景中节省隐私预算：当差分隐私迭代机制在达到最大迭代次数前终止时，以及当DP机制的输出效用不理想时。前者的例子包括迭代优化算法，后者的例子包括训练泛化误差较大的机器学习模型。我们的技术可应用于本文范围之外，用于完善现有DP机制的分析或指导未来机制的设计。
英文摘要：
Differential privacy (DP) is a widely used notion for reasoning about privacy when publishing aggregate data. In this paper, we observe that certain DP mechanisms are amenable to a posteriori privacy analysis that exploits the fact that some outputs leak less information about the input database than others. To exploit this phenomenon, we introduce output differential privacy (ODP) and a new composition experiment, and leverage these new constructs to obtain significant privacy budget savings and improved privacy-utility tradeoffs under composition. All of this comes at no cost in terms of privacy; we do not weaken the privacy guarantee. To demonstrate the applicability of our a posteriori privacy analysis techniques, we analyze two well-known mechanisms: the Sparse Vector Technique and the Propose-Test-Release framework. We then show how our techniques can be used to save privacy budget in more general contexts: when a differentially private iterative mechanism terminates before its maximal number of iterations is reached, and when the output of a DP mechanism provides unsatisfactory utility. Examples of the former include iterative optimization algorithms, whereas examples of the latter include training a machine learning model with a large generalization error. Our techniques can be applied beyond the current paper to refine the analysis of existing DP mechanisms or guide the design of future mechanisms.
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。
