Achieving optimal statistical performance while ensuring the privacy of personal data is a challenging yet crucial objective in modern data analysis. However, characterizing the optimality, particularly the minimax lower bound, under privacy constraints is technically difficult. To address this issue, we propose a novel approach called the score attack, which provides a lower bound on the differential-privacy-constrained minimax risk of parameter estimation. The score attack method is based on the tracing attack concept in differential privacy and can be applied to any statistical model with a well-defined score statistic. It can optimally lower bound the minimax risk of estimating unknown model parameters, up to a logarithmic factor, while ensuring differential privacy for a range of statistical problems. We demonstrate the effectiveness and optimality of this general method in various examples, such as the generalized linear model in both classical and high-dimensional sparse settings, the Bradley-Terry-Luce model for pairwise comparisons, and nonparametric regression over the Sobolev class.
翻译:在现代数据分析中,在确保个人数据隐私的同时实现最佳统计业绩是一项具有挑战性但至关重要的目标。然而,在隐私权限制下,确定最佳性,特别是最低最低约束,在技术上是困难的。为了解决这一问题,我们建议采用称为评分攻击的新颖方法,该方法为不同隐私差异和高度限制的小型参数估计提供了较低约束。得分攻击方法基于不同隐私的追踪攻击概念,可适用于任何具有明确界定的得分统计的统计模式。该方法可以最佳地降低估算未知模型参数的最小最大风险,直至对数系数,同时确保一系列统计问题有不同的隐私。我们在许多例子中展示了这一一般性方法的有效性和最佳性,例如古典和高维稀有环境中的通用线性模型、用于对等比较的布拉德利-特里-卢斯模型,以及索博列夫级的非对数回归。</s>