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)-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 ), where ε ∈ (0, 1) is the privacy parameter and β is the accuracy tolerance. We conclude by initiating the study of a private version of classical shadows to estimate the expectation of multiple observables privately, which promises useful applications for private learning tasks.

Authors

Institutions

Publication Details

Journal
Quantum Science and Technology
Published
2026-11-18
DOI
https://doi.org/10.1088/2058-9565/aec3d0
Citations
3
Primary Topic
Privacy-Preserving Technologies in Data
Type
article
Field-Weighted Citation Impact
2.90

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Privacy-Utility Tradeoffs with Quantum Local Differential Privacy

Sujeet Bhalerao, Theshani Nuradha, Felix Leditzky
3 citations
Quantum Science and Technology
Privacy-Preserving Technologies in Data
2.90
article

Privacy-Utility Tradeoffs with Quantum Local Differential Privacy

Sujeet Bhalerao, Theshani Nuradha, Felix Leditzky
article en
3 citations

Abstract

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)-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 ), where ε ∈ (0, 1) is the privacy parameter and β is the accuracy tolerance. We conclude by initiating the study of a private version of classical shadows to estimate the expectation of multiple observables privately, which promises useful applications for private learning tasks.

Quantum Science and Technology
University of Illinois Urbana-Champaign (US)
National Science Foundation, University of Illinois at Urbana-Champaign
Openalex Percentile: Top 9%
Privacy-Preserving Technologies in Data
2.90
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon