为量子机器学习设计首个差分隐私参数偏移方法，提升隐私与性能平衡。
Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning
- 利用量子梯度固有特性设计差分隐私机制，降低噪声需求。
- 在基准数据集上表现优于传统差分隐私方法，隐私-效用权衡更优。
- 适合关注量子机器学习隐私保护的研究者与开发者。
量子机器学习（QML）虽具显著计算优势，但训练数据隐私保护仍具挑战。经典方法如差分隐私随机梯度下降（DP-SGD）对梯度加噪，却未能利用量子梯度估计的独特性质。本文提出首个专为QML设计的差分隐私参数偏移规则（Q-ShiftDP），通过利用参数偏移法计算的量子梯度所具有的固有有界性和随机性，实现更紧的敏感度分析，减少噪声需求。结合精心校准的高斯噪声与内在量子噪声，提供形式化隐私与效用保证，并证明利用量子噪声可进一步优化隐私-效用权衡。在基准数据集上的实验表明，Q-ShiftDP在QML中持续优于经典差分隐私方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。