何时聚焦增益效用：目标范围 LDP 频率估计与未知物品发现
摘要
本地差分隐私 (LDP) 协议允许在无需受信任数据管理员的情况下收集随机化的客户端消息进行数据分析。此类协议已成功部署于谷歌、苹果和微软等大型科技公司。本文提出了通用计数均值sketch (GCMS) 协议，涵盖许多现有频率估计协议。我们的方法显著改进了通信、隐私和准确性之间的三方权衡。我们还引入了一般化的效用分析框架，以优化参数设计。基于此，我们提出了最优计数均值sketch (OCMS) 框架，用于最小化收集带有目标频率的物品的方差。此外，我们 presenting a novel protocol for collecting data within unknown domain, as our frequency estimation protocols only work effectively with known data domain. Leveraging the stability-based histogram technique alongside the Encryption-Shuffling-Analysis (ESA) framework, our approach employs an auxiliary server to construct histograms without accessing original data messages. This protocol achieves accuracy akin to the central DP model while offering local-like privacy guarantees and substantially lowering computational costs.
关键词
引用
@article{arxiv.2412.17303,
title = {When Focus Enhances Utility: Target Range LDP Frequency Estimation and Unknown Item Discovery},
author = {Bo Jiang and Wanrong Zhang and Donghang Lu and Jian Du and Qiang Yan},
journal= {arXiv preprint arXiv:2412.17303},
year = {2024}
}