Characterizing privacy in quantum machine learning
Open Access
- 19 May 2025
- journal article
- research article
- Published by Springer Nature in npj Quantum Information
- Vol. 11 (1) , 1-15
Abstract
Ensuring data privacy in machine learning models is critical, especially in distributed settings where model gradients are shared among multiple parties for collaborative learning. Motivated by the increasing success of recovering input data from the gradients of classical models, this study investigates the analogous challenge for variational quantum circuits (VQC) as quantum machine learning models. We highlight the crucial role of the dynamical Lie algebra (DLA) in determining privacy vulnerabilities. While the DLA has been linked to the trainability and simulatability of VQC models, we establish its connection to privacy for the first time. We show that properties conducive to VQC trainability, such as a polynomial-sized DLA, also facilitate extracting detailed snapshots of the input, posing a weak privacy breach. We further investigate conditions for a strong privacy breach, where original input data can be recovered from snapshots by classical or quantum-assisted methods. We establish properties of the encoding map, such as classical simulatability, overlap with DLA basis, and its Fourier frequency characteristics that enable such a privacy breach of VQC models. Our framework thus guides the design of quantum machine learning models, balancing trainability and robust privacy protection.Keywords
This publication has 52 references indexed in Scilit:
- A Lie algebraic theory of barren plateaus for deep parameterized quantum circuitsNature Communications, 2024
- Quantum variational algorithms are swamped with trapsNature Communications, 2022
- Quantum federated learning through blind quantum computingScience China Physics, Mechanics & Astronomy, 2021
- A Comprehensive Survey of Loss Functions in Machine LearningAnnals of Data Science, 2020
- Smooth Convex Optimization2018
- Barren plateaus in quantum neural network training landscapesNature Communications, 2018
- Numerical Optimization1999
- Gröbner Bases: An Algorithmic Method in Polynomial Ideal Theory1985
- The complexity of the word problems for commutative semigroups and polynomial idealsAdvances in Mathematics, 1982
- A three-stage variable-shift iteration for polynomial zeros and its relation to generalized rayleigh iterationNumerische Mathematik, 1970