Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2511.01467 · IEEE Transactions on Information Theory

Quantum Information Ordering and Differential Privacy

Ayanava Dasgupta, Naqueeb Ahmad Warsi, Masahito Hayashi

quant-phcs.ITcs.LGSubmitted Nov 3, 2025• Announced Nov 4, 2025• 8 citations• Revised Nov 13, 2025 (v2)
v1 · Nov 3, 2025v2 · Nov 13, 2025v3 · Feb 3, 2026v4 · Oct 5, 2026
arXivHTMLPDF

Abstract

We study quantum differential privacy (QDP) by defining a notion of the order of informativeness between two pairs of quantum states. In particular, we show that if the hypothesis testing divergence of the one pair dominates over that of the other pair, then this dominance holds for every $f$-divergence. This approach completely characterizes $(\varepsilon,δ)$-QDP mechanisms by identifying the most informative $(\varepsilon,δ)$-DP quantum state pairs. We apply this to analyze the stability of quantum differentially private learning algorithms, generalizing classical results to the case $δ>0$. Additionally, we study precise limits for privatized hypothesis testing and privatized quantum parameter estimation, including tight upper-bounds on the quantum Fisher information under QDP. Finally, we establish near-optimal contraction bounds for differentially private quantum channels with respect to the hockey-stick divergence.

DOI
10.1109/TIT.2026.3737562
Comments
Corrected few errors, 52 pages, 3 figures

Related papers

Theory of Privacy and Testing in a Quantum World

Theshani Nuradha

With the surging interest in quantum and hybrid classical-quantum systems, ensuring the privacy of generated quantum data is essential. Quantum differential privacy (QDP) has been introduced to ensure privacy for quantum states. However, the versatility of QDP is limited. We introduce a flexible privacy framework for quantum systems termed as Quantum PP (QPP). We show that QPP is captured exactly by an information-spectrum divergence, endowing the latter with its first operational interpretation. Then this divergence is used to study properties of QPP mechanisms, showcasing distinctions that arise in the quantum setting compared to the classical setting. We introduce the first algorithms that can be used to audit for privacy given a mechanism, which facilitates new approaches with the access to quantum devices. We analyse how the QPP framework provides better privacy-utility tradeoffs with the flexibility to incorporate application-specific criteria.To provide further insights on QPP, we comprehensively study measured hockey-stick divergences that find operational interpretation in the QPP framework as optimal privacy parameters. Studying statistical problems under privacy constraints is vital for understanding the price that we have to pay to ensure privacy. To this end, the contraction of statistical measures and divergences under privacy constraintsis an important technical tool. However, in the quantum setting, this area of research is largely unexplored even for fundamental statistical tasks. We characterize the contraction of quantum divergences under a local variant of quantum privacy, which enables this field of study. We completely characterize the privatized contraction coefficient of the trace distance, among others. Next, we utilize the information-theoretic tools developed to study statistical tasks under privacy constraints. To this end, we characterize the cost of privacy in quantum hypothesis testing and learning expectation of observables while ensuring privacy of quantum states. In sum, this thesis lays a theoretical foundation for ensuring the privacy of quantum data by introducing flexible privacy frameworks tailored to quantum systems. It also evaluates the tradeoffs involved in maintaining privacy during the testing and learning of properties of quantum data, offering information-theoretic tools to study statistical tasks under privacy constraints.

•Jan 1, 2025•0 citations

Quantum Probabilistic Local Differential Privacy: Structural Properties and Sample Complexity Bounds

Xian Shi

Differential privacy provides a rigorous framework for quantifying privacy leakage in data analysis, while its quantum extensions have become increasingly relevant with the development of quantum computing and quantum machine learning. In this work, we introduce and study quantum probabilistic local differential privacy, a relaxation of quantum local differential privacy in which the privacy constraint is allowed to fail on a spectral violation event with low probability. This quantity can be interpreted as the probability under the quantum superoperation of a quantum privacy-loss violation, and is closely related to the acceptance probability of the quantum Neyman-Pearson test at a small threshold. We investigate the basic structural properties of this privacy notion and clarify its relationship with existing forms of quantum differential privacy. We show the properties of quantum probabilistic local differential privacy under tensor-product composition and unitary post-processing, while it is in general neither convex nor closed under post-processing by arbitrary quantum channels. We further characterize when depolarizing noise satisfies quantum probabilistic local differential privacy under several representative scenarios. Finally, we connect quantum probabilistic privacy constraints with statistical inference by deriving a lower bound on probabilistically privatized contraction coefficients in terms of the hockey-stick divergence. As an application, we obtain sample complexity bounds of probabilistically privated asymmetric and symmetric quantum hypothesis testing. These results provide a systematic foundation for studying probabilistic privacy guarantees in quantum information processing and their operational consequences for private quantum statistical inference.

quant-pharXiv:2607.06307•Jul 8, 2026•0 citations

Quantum Advantage for Two-Party Differential Privacy

Daniel Alabi, Emil T. Khabiboulline

We introduce information-theoretically private quantum protocols for two-party Hamming distance when both parties must output the same estimate. Classically, for input length $n$, information-theoretic protocols require $Ω(\sqrt{n})$ error under pure differential privacy and $Ω(\sqrt{n}/\log n)$ error under strong approximate differential privacy, whereas computational security permits $O(1)$ error. In Klauck's honest, nonpreemptive, message-preserving model, we give an $O(n)$-communication quantum protocol with pure $\varepsilon$ quantum differential privacy (QDP) and expected error at most $\frac{2}{\sinh \varepsilon}+γ$, for every $γ>0$. For approximate $(\varepsilon, δ)$ QDP, an exact hockey-stick divergence calculation yields strictly smaller error, while preserving the $O(1)$-versus-$Ω(\sqrt{n}/\log n)$ separation for $δ=o(1/n)$. Thus, quantum communication achieves $O(1)$ information-theoretic error, matching the accuracy available classically only under computational assumptions. The main construction uses a guarded coherent round trip and an equal-Gram rigidity principle that prevents an honest player from retaining input-dependent complementary information. We separate this model from weaker prescribed-channel privacy, which already admits an exact classical realization, and from fully retention-robust security, against which measurement-and-abort attacks remain possible. Therefore, we identify preservation of non-orthogonal quantum messages as a resource for privacy.

quant-pharXiv:2610.02113•Oct 2, 2026•0 citations

Contraction of Private Quantum Channels and Private Quantum Hypothesis Testing

Theshani Nuradha, Mark M. Wilde

A quantum generalized divergence by definition satisfies the data-processing inequality; as such, the relative decrease in such a divergence under the action of a quantum channel is at most one. This relative decrease is formally known as the contraction coefficient of the channel and the divergence. Interestingly, there exist combinations of channels and divergences for which the contraction coefficient is strictly less than one. Furthermore, understanding the contraction coefficient is fundamental for the study of statistical tasks under privacy constraints. To this end, here we establish upper bounds on contraction coefficients for the hockey-stick divergence under privacy constraints, where privacy is quantified with respect to the quantum local differential privacy (QLDP) framework, and we fully characterize the contraction coefficient for the trace distance under privacy constraints. Using the machinery developed, we also determine an upper bound on the contraction of both the Bures distance and quantum relative entropy relative to the normalized trace distance, under QLDP constraints. Next, we apply our findings to establish bounds on the sample complexity of quantum hypothesis testing under privacy constraints. Furthermore, we study various scenarios in which the sample complexity bounds are tight while providing order-optimal quantum channels that achieve those bounds. Lastly, we show how private quantum channels provide fairness and Holevo information stability in quantum learning settings.

arXiv:2406.18651•IEEE Transactions on Information Theory•Jan 9, 2025•26 citations

When Does Quantum Differential Privacy Compose?

Daniel Alabi, Theshani Nuradha

Composition is a cornerstone of classical differential privacy, enabling strong end-to-end guarantees for complex algorithms through composition theorems (e.g., basic and advanced). In the quantum setting, however, privacy is defined operationally against arbitrary measurements, and classical composition arguments based on scalar privacy-loss random variables no longer apply. As a result, it has remained unclear when meaningful composition guarantees can be obtained for quantum differential privacy (QDP). In this work, we clarify both the limitations and possibilities of composition in the quantum setting. We first show that classical-style composition fails in full generality for POVM-based approximate QDP: even quantum channels that are individually perfectly private can completely lose privacy when combined through correlated joint implementations. We then identify a setting in which clean composition guarantees can be restored. For tensor-product channels acting on product neighboring inputs, we introduce a quantum moments accountant based on an operator-valued notion of privacy loss and a matrix moment-generating function. Although the resulting Rényi-type divergence does not satisfy a data-processing inequality, we prove that controlling its moments suffices to bound measured Rényi divergence, yielding operational privacy guarantees against arbitrary measurements. This leads to advanced-composition-style bounds with the same leading-order behavior as in the classical theory. Our results demonstrate that meaningful composition theorems for quantum differential privacy require carefully articulated structural assumptions on channels, inputs, and adversarial measurements, and provide a principled framework for understanding which classical ideas do and do not extend to the quantum setting.

quant-pharXiv:2601.00337•Leibniz international proceedings in informatics•Jan 2, 2026•4 citations

Optimal Quantum Differential Privacy via Fisher Information Spectral Analysis

Justice Owusu Agyemang, Jerry John Kponyo, Elliot Amponsah +1 more

The Quantum Fisher Information (QFI) metric governs a fundamental duality: it quantifies both how precisely a parameter can be estimated (metrology) and how distinguishable two quantum states are (privacy). We exploit this duality to establish a geometry-aware framework for quantum differential privacy (DP) that replaces isotropic depolarizing noise with direction-dependent noise aligned to the QFI eigenstructure of the quantum embedding. We prove six principal theorems: (1) the minimax-optimal mechanism concentrates the noise budget in the dominant QFI eigenmode, achieving $\varepsilon = (Δ^2/2)λ_{\max}(1-cγ)$ with $O(d/λ_{\max})$ advantage; (2) mixed-state QFI decomposition reveals that dephasing in the adversary's basis $\textit{increases}$ accessible information, while misaligned-basis dephasing provides constructive privacy amplification from hardware noise; (3) a tight privacy $-$ utility uncertainty relation $\varepsilon \cdot (1 - F) \ge \frac{Δ^2}{2}\frac{\operatorname{Tr}(F)}{d}$; (4) adaptive QFI estimation converging at $O(1/\sqrt{n})$ yields $1.92\times$ tighter bounds; (5) QFI-aligned composition saturates at $O(1)$ versus $O(k)$ for standard composition; and (6) hardware noise can be harnessed for privacy amplification. Adversarial vulnerabilities, Wasserstein guarantees, subspace projection, and a zero-knowledge audit protocol follow as corollaries. Results are validated on Qiskit Aer GPU simulations, IBM Quantum hardware (ibm_fez, 156 qubits), and against classical DP baselines, achieving equivalent utility at $\varepsilon \approx 0.001$ versus $\varepsilon \approx 4800$ for classical DP.

quant-pharXiv:2605.24166•May 26, 2026•0 citations
We study quantum differential privacy (QDP) by defining a notion of the order of informativeness between two pairs of quantum states. In particular, we show that if the hypothesis testing divergence of the one pair dominates over that of the other pair, then this dominance holds for every fff-divergence. This approach completely characterizes (ε,δ)(\varepsilon,δ)(ε,δ)-QDP mechanisms by identifying the most informative (ε,δ)(\varepsilon,δ)(ε,δ)-DP quantum state pairs. We apply this to analyze the stability of quantum differentially private learning algorithms, generalizing classical results to the case δ>0δ>0δ>0. Additionally, we study precise limits for privatized hypothesis testing and privatized quantum parameter estimation, including tight upper-bounds on the quantum Fisher information under QDP. Finally, we establish near-optimal contraction bounds for differentially private quantum channels with respect to the hockey-stick divergence.
With the surging interest in quantum and hybrid classical-quantum systems, ensuring the privacy of generated quantum data is essential. Quantum differential privacy (QDP) has been introduced to ensure privacy for quantum states. However, the versatility of QDP is limited. We introduce a flexible privacy framework for quantum systems termed as Quantum PP (QPP). We show that QPP is captured exactly by an information-spectrum divergence, endowing the latter with its first operational interpretation. Then this divergence is used to study properties of QPP mechanisms, showcasing distinctions that arise in the quantum setting compared to the classical setting. We introduce the first algorithms that can be used to audit for privacy given a mechanism, which facilitates new approaches with the access to quantum devices. We analyse how the QPP framework provides better privacy-utility tradeoffs with the flexibility to incorporate application-specific criteria.To provide further insights on QPP, we comprehensively study measured hockey-stick divergences that find operational interpretation in the QPP framework as optimal privacy parameters. Studying statistical problems under privacy constraints is vital for understanding the price that we have to pay to ensure privacy. To this end, the contraction of statistical measures and divergences under privacy constraintsis an important technical tool. However, in the quantum setting, this area of research is largely unexplored even for fundamental statistical tasks. We characterize the contraction of quantum divergences under a local variant of quantum privacy, which enables this field of study. We completely characterize the privatized contraction coefficient of the trace distance, among others. Next, we utilize the information-theoretic tools developed to study statistical tasks under privacy constraints. To this end, we characterize the cost of privacy in quantum hypothesis testing and learning expectation of observables while ensuring privacy of quantum states. In sum, this thesis lays a theoretical foundation for ensuring the privacy of quantum data by introducing flexible privacy frameworks tailored to quantum systems. It also evaluates the tradeoffs involved in maintaining privacy during the testing and learning of properties of quantum data, offering information-theoretic tools to study statistical tasks under privacy constraints.
Differential privacy provides a rigorous framework for quantifying privacy leakage in data analysis, while its quantum extensions have become increasingly relevant with the development of quantum computing and quantum machine learning. In this work, we introduce and study quantum probabilistic local differential privacy, a relaxation of quantum local differential privacy in which the privacy constraint is allowed to fail on a spectral violation event with low probability. This quantity can be interpreted as the probability under the quantum superoperation of a quantum privacy-loss violation, and is closely related to the acceptance probability of the quantum Neyman-Pearson test at a small threshold. We investigate the basic structural properties of this privacy notion and clarify its relationship with existing forms of quantum differential privacy. We show the properties of quantum probabilistic local differential privacy under tensor-product composition and unitary post-processing, while it is in general neither convex nor closed under post-processing by arbitrary quantum channels. We further characterize when depolarizing noise satisfies quantum probabilistic local differential privacy under several representative scenarios. Finally, we connect quantum probabilistic privacy constraints with statistical inference by deriving a lower bound on probabilistically privatized contraction coefficients in terms of the hockey-stick divergence. As an application, we obtain sample complexity bounds of probabilistically privated asymmetric and symmetric quantum hypothesis testing. These results provide a systematic foundation for studying probabilistic privacy guarantees in quantum information processing and their operational consequences for private quantum statistical inference.
We introduce information-theoretically private quantum protocols for two-party Hamming distance when both parties must output the same estimate. Classically, for input length nnn, information-theoretic protocols require Ω(n)Ω(\sqrt{n})Ω(n​) error under pure differential privacy and Ω(n/log⁡n)Ω(\sqrt{n}/\log n)Ω(n​/logn) error under strong approximate differential privacy, whereas computational security permits O(1)O(1)O(1) error. In Klauck's honest, nonpreemptive, message-preserving model, we give an O(n)O(n)O(n)-communication quantum protocol with pure ε\varepsilonε quantum differential privacy (QDP) and expected error at most 2sinh⁡ε+γ\frac{2}{\sinh \varepsilon}+γsinhε2​+γ, for every γ>0γ>0γ>0. For approximate (ε,δ)(\varepsilon, δ)(ε,δ) QDP, an exact hockey-stick divergence calculation yields strictly smaller error, while preserving the O(1)O(1)O(1)-versus-Ω(n/log⁡n)Ω(\sqrt{n}/\log n)Ω(n​/logn) separation for δ=o(1/n)δ=o(1/n)δ=o(1/n). Thus, quantum communication achieves O(1)O(1)O(1) information-theoretic error, matching the accuracy available classically only under computational assumptions. The main construction uses a guarded coherent round trip and an equal-Gram rigidity principle that prevents an honest player from retaining input-dependent complementary information. We separate this model from weaker prescribed-channel privacy, which already admits an exact classical realization, and from fully retention-robust security, against which measurement-and-abort attacks remain possible. Therefore, we identify preservation of non-orthogonal quantum messages as a resource for privacy.
A quantum generalized divergence by definition satisfies the data-processing inequality; as such, the relative decrease in such a divergence under the action of a quantum channel is at most one. This relative decrease is formally known as the contraction coefficient of the channel and the divergence. Interestingly, there exist combinations of channels and divergences for which the contraction coefficient is strictly less than one. Furthermore, understanding the contraction coefficient is fundamental for the study of statistical tasks under privacy constraints. To this end, here we establish upper bounds on contraction coefficients for the hockey-stick divergence under privacy constraints, where privacy is quantified with respect to the quantum local differential privacy (QLDP) framework, and we fully characterize the contraction coefficient for the trace distance under privacy constraints. Using the machinery developed, we also determine an upper bound on the contraction of both the Bures distance and quantum relative entropy relative to the normalized trace distance, under QLDP constraints. Next, we apply our findings to establish bounds on the sample complexity of quantum hypothesis testing under privacy constraints. Furthermore, we study various scenarios in which the sample complexity bounds are tight while providing order-optimal quantum channels that achieve those bounds. Lastly, we show how private quantum channels provide fairness and Holevo information stability in quantum learning settings.
Composition is a cornerstone of classical differential privacy, enabling strong end-to-end guarantees for complex algorithms through composition theorems (e.g., basic and advanced). In the quantum setting, however, privacy is defined operationally against arbitrary measurements, and classical composition arguments based on scalar privacy-loss random variables no longer apply. As a result, it has remained unclear when meaningful composition guarantees can be obtained for quantum differential privacy (QDP). In this work, we clarify both the limitations and possibilities of composition in the quantum setting. We first show that classical-style composition fails in full generality for POVM-based approximate QDP: even quantum channels that are individually perfectly private can completely lose privacy when combined through correlated joint implementations. We then identify a setting in which clean composition guarantees can be restored. For tensor-product channels acting on product neighboring inputs, we introduce a quantum moments accountant based on an operator-valued notion of privacy loss and a matrix moment-generating function. Although the resulting Rényi-type divergence does not satisfy a data-processing inequality, we prove that controlling its moments suffices to bound measured Rényi divergence, yielding operational privacy guarantees against arbitrary measurements. This leads to advanced-composition-style bounds with the same leading-order behavior as in the classical theory. Our results demonstrate that meaningful composition theorems for quantum differential privacy require carefully articulated structural assumptions on channels, inputs, and adversarial measurements, and provide a principled framework for understanding which classical ideas do and do not extend to the quantum setting.
The Quantum Fisher Information (QFI) metric governs a fundamental duality: it quantifies both how precisely a parameter can be estimated (metrology) and how distinguishable two quantum states are (privacy). We exploit this duality to establish a geometry-aware framework for quantum differential privacy (DP) that replaces isotropic depolarizing noise with direction-dependent noise aligned to the QFI eigenstructure of the quantum embedding. We prove six principal theorems: (1) the minimax-optimal mechanism concentrates the noise budget in the dominant QFI eigenmode, achieving ε=(Δ2/2)λmax⁡(1−cγ)\varepsilon = (Δ^2/2)λ_{\max}(1-cγ)ε=(Δ2/2)λmax​(1−cγ) with O(d/λmax⁡)O(d/λ_{\max})O(d/λmax​) advantage; (2) mixed-state QFI decomposition reveals that dephasing in the adversary's basis increases\textit{increases}increases accessible information, while misaligned-basis dephasing provides constructive privacy amplification from hardware noise; (3) a tight privacy −-− utility uncertainty relation ε⋅(1−F)≥Δ22Tr⁡(F)d\varepsilon \cdot (1 - F) \ge \frac{Δ^2}{2}\frac{\operatorname{Tr}(F)}{d}ε⋅(1−F)≥2Δ2​dTr(F)​; (4) adaptive QFI estimation converging at O(1/n)O(1/\sqrt{n})O(1/n​) yields 1.92×1.92\times1.92× tighter bounds; (5) QFI-aligned composition saturates at O(1)O(1)O(1) versus O(k)O(k)O(k) for standard composition; and (6) hardware noise can be harnessed for privacy amplification. Adversarial vulnerabilities, Wasserstein guarantees, subspace projection, and a zero-knowledge audit protocol follow as corollaries. Results are validated on Qiskit Aer GPU simulations, IBM Quantum hardware (ibm_fez, 156 qubits), and against classical DP baselines, achieving equivalent utility at ε≈0.001\varepsilon \approx 0.001ε≈0.001 versus ε≈4800\varepsilon \approx 4800ε≈4800 for classical DP.