BriefGPT.xyz
May, 2016
集中式差分隐私:简化、扩展和下限
Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
HTML
PDF
Mark Bun, Thomas Steinke
TL;DR
本文探讨了“浓缩差分隐私”的概念,将其用Renyi散度重新构建,得到更为精确的量化结果,并探讨了一些相关问题。同时,本文还通过给出“近似浓缩差分隐私”的定义,将这种方法与“近似差分隐私”相统一。
Abstract
"
concentrated differential privacy
" was recently introduced by Dwork and Rothblum as a relaxation of differential privacy, which permits sharper analyses of many
privacy-preserving computations
. We present an alt
→