通用实用性最大化隐私机制
Universally Utility-Maximizing Privacy Mechanisms
摘要：
一个公布关于含有敏感数据的统计数据库的信息的机制必须解决实用性和隐私性之间的权衡问题。隐私可以使用{ \em差分隐私}的框架来严格量化，该框架要求无论是否包括或排除给定的数据库行，机制的输出分布都几乎相同。本文的目标是强大的和一般的效用保证，受差分隐私。我们追求的机制，保证接近最佳的效用，每一个潜在的用户，独立于它的边信息（建模为一个先验分布的查询结果）和偏好（通过一个损失函数建模）。我们的主要结果是：对于每个固定计数查询和差分隐私级别，存在{ \em几何机制} $M^*$ --简单且充分研究的拉普拉斯机制的离散变体--即，对于每个可能的用户，{ \em同时期望损失最小化}服从差分隐私约束。这是一个非常强的实用性保证：{ \em every}潜在用户$u$，无论其附带信息和偏好是什么，从$M^*$获得的实用性与从与最佳地为$u$定制的差异私有机制$M_u$交互获得的一样多。
英文摘要：
A mechanism for releasing information about a statistical database with sensitive data must resolve a trade-off between utility and privacy. Privacy can be rigorously quantified using the framework of {\em differential privacy}, which requires that a mechanism's output distribution is nearly the same whether or not a given database row is included or excluded. The goal of this paper is strong and general utility guarantees, subject to differential privacy. We pursue mechanisms that guarantee near-optimal utility to every potential user, independent of its side information (modeled as a prior distribution over query results) and preferences (modeled via a loss function). Our main result is: for each fixed count query and differential privacy level, there is a {\em geometric mechanism} $M^*$ -- a discrete variant of the simple and well-studied Laplace mechanism -- that is {\em simultaneously expected loss-minimizing} for every possible user, subject to the differential privacy constraint. This is an extremely strong utility guarantee: {\em every} potential user $u$, no matter what its side information and preferences, derives as much utility from $M^*$ as from interacting with a differentially private mechanism $M_u$ that is optimally tailored to $u$.
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。
