BriefGPT.xyz
Jun, 2024
扰动和投影：差分隐私的相似性和边际
Perturb-and-Project: Differentially Private Similarities and Marginals
HTML
PDF
Vincent Cohen-Addad, Tommaso d'Orsi, Alessandro Epasto, Vahab Mirrokni, Peilin Zhong
TL;DR
重新审视了差分隐私的输入扰动框架，介绍了有效算法用于保护隐私的发布余弦相似度和计算多特征边际查询，扩展结果适用于稀疏数据集，提供理论视角解释快速输入扰动算法在实践中的良好表现。
Abstract
We revisit the
input perturbations
framework for
differential privacy
where noise is added to the input $A\in \mathcal{S}$ and the result is then projected back to the space of admissible datasets $\mathcal{S}$.
→