Black-Box Auditing of Quantum Model: Lifted Differential Privacy with Quantum Canaries
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909965382320128 |
|---|---|
| author | Song, Baobao Pokhrel, Shiva Raj Vasilakos, Athanasios V. Zhu, Tianqing Li, Gang |
| author_facet | Song, Baobao Pokhrel, Shiva Raj Vasilakos, Athanasios V. Zhu, Tianqing Li, Gang |
| contents | Quantum machine learning (QML) promises significant computational advantages, yet models trained on sensitive data risk memorizing individual records, creating serious privacy vulnerabilities. While Quantum Differential Privacy (QDP) mechanisms provide theoretical worst-case guarantees, they critically lack empirical verification tools for deployed models. We introduce the first black-box privacy auditing framework for QML based on Lifted Quantum Differential Privacy, leveraging quantum canaries (strategically offset-encoded quantum states) to detect memorization and precisely quantify privacy leakage during training. Our framework establishes a rigorous mathematical connection between canary offset and trace distance bounds, deriving empirical lower bounds on privacy budget consumption that bridge the critical gap between theoretical guarantees and practical privacy verification. Comprehensive evaluations across both simulated and physical quantum hardware demonstrate our framework's effectiveness in measuring actual privacy loss in QML models, enabling robust privacy verification in QML systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14388 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Black-Box Auditing of Quantum Model: Lifted Differential Privacy with Quantum Canaries Song, Baobao Pokhrel, Shiva Raj Vasilakos, Athanasios V. Zhu, Tianqing Li, Gang Machine Learning Quantum machine learning (QML) promises significant computational advantages, yet models trained on sensitive data risk memorizing individual records, creating serious privacy vulnerabilities. While Quantum Differential Privacy (QDP) mechanisms provide theoretical worst-case guarantees, they critically lack empirical verification tools for deployed models. We introduce the first black-box privacy auditing framework for QML based on Lifted Quantum Differential Privacy, leveraging quantum canaries (strategically offset-encoded quantum states) to detect memorization and precisely quantify privacy leakage during training. Our framework establishes a rigorous mathematical connection between canary offset and trace distance bounds, deriving empirical lower bounds on privacy budget consumption that bridge the critical gap between theoretical guarantees and practical privacy verification. Comprehensive evaluations across both simulated and physical quantum hardware demonstrate our framework's effectiveness in measuring actual privacy loss in QML models, enabling robust privacy verification in QML systems. |
| title | Black-Box Auditing of Quantum Model: Lifted Differential Privacy with Quantum Canaries |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.14388 |