This paper introduces the \texttt{multi-freq-ldpy} Python package for multiple frequency estimation under Local Differential Privacy (LDP) guarantees. LDP is a gold standard for achieving local privacy with several real-world implementations by big tech companies such as Google, Apple, and Microsoft. The primary application of LDP is frequency (or histogram) estimation, in which the aggregator estimates the number of times each value has been reported. The presented package provides an easy-to-use and fast implementation of state-of-the-art solutions and LDP protocols for frequency estimation of: multiple attributes (i.e., multidimensional data), multiple collections (i.e., longitudinal data), and both multiple attributes/collections. Multi-Freq-LDPy is built on the well-established \textit{Numpy} package -- a \textit{de facto} standard for scientific computing in Python -- and the \textit{Numba} package for fast execution. These features are illustrated in this demo paper with different tutorial-like case studies. This package is open-source and publicly available under an MIT license via GitHub https://github.com/hharcolezi/multi-freq-ldpy and can be installed via PyPi.
翻译:本文介绍本地差异隐私(LDP) 保障下多频率估算的\ textt{ 多重- freq- ldpy} Python 套件。 LDP 是实现本地隐私的黄金标准, 由谷歌、 苹果和微软等大技术公司实施若干真实世界的实施。 LDP 的主要应用是频度( 或直方图) 估算, 其中聚合器估算了每个值的报告次数。 提供的套件提供了一种方便使用和快速实施最新解决方案和LDP 协议的频率估算: 多属性( i. e.) 、 多收藏( i. 长方位数据) 和多个属性/ 收藏。 多功能- Freq- LDPy 是建立在久经久的\ textitit{ numpy} 套件上, 其中聚合器估算了每个值的频率。 所展示的套件为快速执行, 这些特征在这份制式文件中通过像质性 Prialtial- main- mindal/ giqubral 案例研究加以说明。 此套件可公开使用。