跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2602.10510 · v2

Privacy-Utility Tradeoffs with Quantum Local Differential Privacy

量子局部差分隐私下的隐私-效用权衡

首次提交 2026-02-11 12:21
版本更新 2026-11-20 00:50
雷达观测 2026-11-20 12:52
arXiv ↗PDF ↗

摘要

When sensitive information is encoded in data, it is important to ensure the privacy of information when attempting to learn useful information from the data. There is a natural tradeoff whereby increasing privacy requirements may decrease the utility of a learning protocol. In the quantum setting of differential privacy, such tradeoffs between privacy and utility have so far remained largely unexplored. In this work, we study optimal privacy-utility tradeoffs for both generic and application-specific utility metrics when privacy is quantified by (ε,δ)(\varepsilon,δ)-quantum local differential privacy. In the generic setting, we focus on optimizing fidelity and trace distance between the original state and the privatized state. We show that the depolarizing mechanism achieves the optimal utility for given privacy requirements. We then study the specific application of learning the expectation of an observable with respect to an input state when only given access to privatized states. We derive a lower bound on the number of samples of privatized data required to achieve a fixed accuracy guarantee with high probability. To prove this result, we employ existing lower bounds on private quantum hypothesis testing, thus showcasing the first operational use of them. We also devise private mechanisms that achieve optimal sample complexity with respect to the privacy parameters and accuracy parameters, demonstrating that utility can be significantly improved for specific tasks in contrast to the generic setting. In addition, we show that the number of samples required to privately learn observable expectation values scales as Θ((εβ)−2)Θ((\varepsilon β)^{-2}), where ε∈(0,1)\varepsilon \in (0,1) is the privacy parameter and ββ is the accuracy tolerance. We conclude by initiating the study of private classical shadows, which promise useful applications for private learning tasks.

作者备注:v2:accepted to Quantum Science and Technology, November 2026, 25pages; v1:23 pages, 2 figures

AI 论文解读

基于摘要 · 非全文审阅

研究在(ε,δ)-量子局部差分隐私下,通用与特定任务中隐私与效用的最优权衡,并给出学习可观测量期望的样本复杂度。

正在读取账号与研究记录…

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-20 00:50 · 最新观测版本

Privacy-Utility Tradeoffs with Quantum Local Differential Privacy

When sensitive information is encoded in data, it is important to ensure the privacy of information when attempting to learn useful information from the data. There is a natural tradeoff whereby increasing privacy requirements may decrease the utility of a learning protocol. In the quantum setting of differential privacy, such tradeoffs between privacy and utility have so far remained largely unexplored. In this work, we study optimal privacy-utility tradeoffs for both generic and application-specific utility metrics when privacy is quantified by (ε,δ)(\varepsilon,δ)-quantum local differential privacy. In the generic setting, we focus on optimizing fidelity and trace distance between the original state and the privatized state. We show that the depolarizing mechanism achieves the optimal utility for given privacy requirements. We then study the specific application of learning the expectation of an observable with respect to an input state when only given access to privatized states. We derive a lower bound on the number of samples of privatized data required to achieve a fixed accuracy guarantee with high probability. To prove this result, we employ existing lower bounds on private quantum hypothesis testing, thus showcasing the first operational use of them. We also devise private mechanisms that achieve optimal sample complexity with respect to the privacy parameters and accuracy parameters, demonstrating that utility can be significantly improved for specific tasks in contrast to the generic setting. In addition, we show that the number of samples required to privately learn observable expectation values scales as Θ((εβ)−2)Θ((\varepsilon β)^{-2}), where ε∈(0,1)\varepsilon \in (0,1) is the privacy parameter and ββ is the accuracy tolerance. We conclude by initiating the study of private classical shadows, which promise useful applications for private learning tasks.

查看此版本解读 →查看此版本原文 ↗