论文标题
高斯差异隐私的完全自适应组成
Fully Adaptive Composition for Gaussian Differential Privacy
论文作者
论文摘要
我们表明，高斯差异隐私，这是一种针对加斯噪声分析的差异隐私的变体，即使在完全自适应分析师的情况下也可以优雅地构成。这样的分析师选择机制（待在敏感的数据集上运行）及其隐私预算，也就是基于以前在相同数据集上运行的其他机制的答案。在罗杰斯（Rogers），罗斯（Roth），乌尔曼（Ullman）和瓦丹（Vadhan）的语言中，这给出了GDP的过滤器，其参数与非适应性成分相同。
We show that Gaussian Differential Privacy, a variant of differential privacy tailored to the analysis of Gaussian noise addition, composes gracefully even in the presence of a fully adaptive analyst. Such an analyst selects mechanisms (to be run on a sensitive data set) and their privacy budgets adaptively, that is, based on the answers from other mechanisms run previously on the same data set. In the language of Rogers, Roth, Ullman and Vadhan, this gives a filter for GDP with the same parameters as for nonadaptive composition.
