Black-Box Auditing of Quantum Model: Lifted Differential Privacy with Quantum Canaries
This addresses privacy vulnerabilities in quantum machine learning for sensitive data applications, representing a novel verification tool rather than an incremental improvement.
The paper tackles the problem of verifying privacy guarantees in quantum machine learning models by introducing the first black-box auditing framework based on Lifted Quantum Differential Privacy, which uses quantum canaries to detect memorization and quantify privacy leakage during training with comprehensive evaluations on simulated and physical quantum hardware.
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.