Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning

TL;DR

This paper introduces Q-ShiftDP, a novel differentially private mechanism tailored for quantum machine learning that leverages quantum-specific properties to improve privacy-utility trade-offs over classical methods.

Contribution

It presents the first privacy mechanism specifically designed for QML using the parameter-shift rule, combining quantum and classical noise for enhanced privacy guarantees.

Findings

Q-ShiftDP outperforms classical DP methods in QML tasks.

Leveraging quantum noise improves privacy-utility balance.

Tighter sensitivity analysis reduces noise requirements.

Abstract

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.