论文标题
通过Edgeworth扩展，高斯差异隐私的尖锐组成范围
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
论文作者
论文摘要
通常通过许多算法对包含敏感信息的数据集进行顺序分析。这在差异隐私中提出了一个基本问题，即整体隐私如何降低组成。为了解决这个问题，我们使用Edgeworth扩展在最近提出的F-Differential隐私的框架中介绍了一个分析和尖锐的隐私范围。与使用中央限制定理的现有组成定理相反，我们在组成下的新隐私范围通过利用Edgeworth扩展的精制近似精度提高了紧密度。我们的方法易于实施，并且对于任何数量的构图，我们的方法在计算上有效。这些新界限的优势通过渐近误差分析和量化用于训练私人深神经网络的嘈杂随机梯度下降的总体隐私保证的应用来证实。
Datasets containing sensitive information are often sequentially analyzed by many algorithms. This raises a fundamental question in differential privacy regarding how the overall privacy bound degrades under composition. To address this question, we introduce a family of analytical and sharp privacy bounds under composition using the Edgeworth expansion in the framework of the recently proposed f-differential privacy. In contrast to the existing composition theorems using the central limit theorem, our new privacy bounds under composition gain improved tightness by leveraging the refined approximation accuracy of the Edgeworth expansion. Our approach is easy to implement and computationally efficient for any number of compositions. The superiority of these new bounds is confirmed by an asymptotic error analysis and an application to quantifying the overall privacy guarantees of noisy stochastic gradient descent used in training private deep neural networks.
