Quantum Pufferfish Privacy: A Flexible Privacy Framework for Quantum Systems
arXiv:2306.13054 · doi:10.1109/TIT.2024.3404927
Abstract
We propose a versatile privacy framework for quantum systems, termed quantum pufferfish privacy (QPP). Inspired by classical pufferfish privacy, our formulation generalizes and addresses limitations of quantum differential privacy by offering flexibility in specifying private information, feasible measurements, and domain knowledge. We show that QPP can be equivalently formulated in terms of the Datta-Leditzky information spectrum divergence, thus providing the first operational interpretation thereof. We reformulate this divergence as a semi-definite program and derive several properties of it, which are then used to prove convexity, composability, and post-processing of QPP mechanisms. Parameters that guarantee QPP of the depolarization mechanism are also derived. We analyze the privacy-utility tradeoff of general QPP mechanisms and, again, study the depolarization mechanism as an explicit instance. The QPP framework is then applied to privacy auditing for identifying privacy violations via a hypothesis testing pipeline that leverages quantum algorithms. Connections to quantum fairness and other quantum divergences are also explored and several variants of QPP are examined.
arXiv commentv2: 33 pages, 9 figures, accepted to IEEE Transactions on Information Theory
References in corpus (40)
- Variational Quantum Algorithms
- Noisy intermediate-scale quantum (NISQ) algorithms
- RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
- Quantum principal component analysis
- Renyi Differential Privacy
- On quantum Renyi entropies: a new generalization and some properties
- Quantum singular value transformation and beyond: exponential improvements for quantum matrix arithmetics
- Strong converse for the classical capacity of entanglement-breaking and Hadamard channels via a sandwiched Renyi relative entropy
- Min- and Max- Relative Entropies and a New Entanglement Monotone
- Quantum Data Hiding
- Randomizing quantum states: Constructions and applications
- Quantum Information Processing with Finite Resources -- Mathematical Foundations
- A Sharp Fannes-type Inequality for the von Neumann Entropy
- Hiding bits in Bell states
- Monotonicity of a relative Rényi entropy
- Distinguishability and Accessible Information in Quantum Theory
- Differential Privacy as a Mutual Information Constraint
- Hiding classical data in multi-partite quantum states
- Distinguishability of quantum states under restricted families of measurements with an application to quantum data hiding
- Quantum noise protects quantum classifiers against adversaries
- Detecting Violations of Differential Privacy
- Different quantum f-divergences and the reversibility of quantum operations
- The Quantum Wasserstein Distance of Order 1
- Principles of Quantum Communication Theory: A Modern Approach
- Approximate Degradable Quantum Channels
- Resource theory of asymmetric distinguishability
- Multiparty data hiding of quantum information
- Second-order asymptotics for source coding, dense coding and pure-state entanglement conversions
- Ultimate data hiding in quantum mechanics and beyond
- Optimized quantum f-divergences and data processing
- New Quantum Algorithms for Computing Quantum Entropies and Distances
- Estimating distinguishability measures on quantum computers
- Quantum Differentially Private Sparse Regression Learning
- Fast Quantum Algorithms for Trace Distance Estimation
- Postselected quantum hypothesis testing
- Symmetric distinguishability as a quantum resource
- Pufferfish Privacy: An Information-Theoretic Study
- Differential Privacy Amplification in Quantum and Quantum-inspired Algorithms
- Quantum data hiding in the presence of noise
- Private learning implies quantum stability
Cited by in corpus (8)
- New Quantum Algorithms for Computing Quantum Entropies and Distances
- Fast Quantum Algorithms for Trace Distance Estimation
- Contraction of Private Quantum Channels and Private Quantum Hypothesis Testing
- An invitation to the sample complexity of quantum hypothesis testing
- Measured Hockey-Stick Divergence and its Applications to Quantum Pufferfish Privacy
- Extendible quantum measurements and limitations on classical communication
- Sample Complexity Bounds for Scalar Parameter Estimation Under Quantum Differential Privacy
- Tight relations and equivalences between smooth relative entropies