BriefGPT.xyz
Jun, 2021
差分隐私的数值组成
Numerical Composition of Differential Privacy
HTML
PDF
Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz
TL;DR
提供了一种快速算法，可以将差分隐私算法的隐私保证优化到任意精度，并使用隐私损失随机变量的概念来量化差分隐私算法的隐私损失，该算法可以加速隐私计算几个数量级同时保持类似的准确性。
Abstract
We give a fast algorithm to optimally compose
privacy guarantees
of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of
privacy loss random variables
to quantify the
→