A bounded-noise mechanism for differential privacy

A bounded-noise mechanism for differential privacy
复制标题

差分隐私的有界噪声机制

DOI:
--
复制
发表时间:
2020
期刊:
Annual Conference Computational Learning Theory
影响因子:
--
通讯作者:
Gil Kur
Gil Kur
中科院分区:
--
文献类型:
--
作者:
Y. Dagan;Gil Kur

文献摘要

参考文献

被引文献

相似文献

我们提出了一个渐近最优的$(\epsilon,\Delta)$差分私有机制,用于回答多个适应性询问的$\Delta$敏感查询,解决了Steinke和Ullman[2020]的猜想。我们的算法有一个显著的优势,它给每个查询增加了独立的有界噪声,从而提供了一个绝对的误差界。此外,我们将我们的算法应用到自适应数据分析中,获得了使用有限样本回答关于某些潜在分布的多个查询的改进的保证。数值计算表明,在许多标准设置下,有界噪声机制的性能优于高斯机制。
We present an asymptotically optimal $(\epsilon,\delta)$ differentially private mechanism for answering multiple, adaptively asked, $\Delta$-sensitive queries, settling the conjecture of Steinke and Ullman [2020]. Our algorithm has a significant advantage that it adds independent bounded noise to each query, thus providing an absolute error bound. Additionally, we apply our algorithm in adaptive data analysis, obtaining an improved guarantee for answering multiple queries regarding some underlying distribution using a finite sample. Numerical computations show that the bounded-noise mechanism outperforms the Gaussian mechanism in many standard settings.
DOI: 10.4230/lipics.forc.2021.1
发表时间: 2021
影响因子: --
作者:
Ganesh, Arun;Zhao, Jiazheng
通讯作者: Zhao, Jiazheng