Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908807993491456 |
|---|---|
| author | Ngo, Hoang M. Hoang-Xuan, Nhat Nguyen, Quan Do, Nguyen Shin, Incheol Thai, My T. |
| author_facet | Ngo, Hoang M. Hoang-Xuan, Nhat Nguyen, Quan Do, Nguyen Shin, Incheol Thai, My T. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02962 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning Ngo, Hoang M. Hoang-Xuan, Nhat Nguyen, Quan Do, Nguyen Shin, Incheol Thai, My T. Machine Learning Cryptography and Security 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. |
| title | Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2602.02962 |