Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning
This addresses privacy concerns in QML, offering a domain-specific improvement over existing methods.
The paper tackles the challenge of preserving training data privacy in quantum machine learning (QML) by introducing Q-ShiftDP, a differentially private parameter-shift rule tailored to QML, which reduces noise requirements and outperforms classical DP methods on benchmark datasets.
Quantum Machine Learning (QML) promises significant computational advantages, but preserving training data privacy remains challenging. Classical approaches like differentially private stochastic gradient descent (DP-SGD) add noise to gradients but fail to exploit the unique properties of quantum gradient estimation. In this work, we introduce the Differentially Private Parameter-Shift Rule (Q-ShiftDP), the first privacy mechanism tailored to QML. By leveraging the inherent boundedness and stochasticity of quantum gradients computed via the parameter-shift rule, Q-ShiftDP enables tighter sensitivity analysis and reduces noise requirements. We combine carefully calibrated Gaussian noise with intrinsic quantum noise to provide formal privacy and utility guarantees, and show that harnessing quantum noise further improves the privacy-utility trade-off. Experiments on benchmark datasets demonstrate that Q-ShiftDP consistently outperforms classical DP methods in QML.