# Black-Box Auditing of Quantum Model: Lifted Differential Privacy with Quantum Canaries

arXiv: https://arxiv.org/abs/2512.14388 · HTML: https://mlsanity.com/paper/2512.14388/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Builds on (most cited first, 14 of 14)

- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Barren plateaus in quantum neural network training landscapes](https://mlsanity.com/paper/1803.11173/) (2018)
- [Auditing Differentially Private Machine Learning: How Private is Private SGD?](https://mlsanity.com/paper/2006.07709/) (2020)
- [Privacy Auditing with One (1) Training Run](https://mlsanity.com/paper/2305.08846/) (2023)
- [Quantum noise protects quantum classifiers against adversaries](https://mlsanity.com/paper/2003.09416/) (2020)
- [Quantum machine learning for image classification](https://mlsanity.com/paper/2304.09224/) (2023)
- [Quantum Differential Privacy: An Information Theory Perspective](https://mlsanity.com/paper/2202.10717/) (2022)
- [Privacy Auditing of Large Language Models](https://mlsanity.com/paper/2503.06808/) (2025)
- [Unleashing the Power of Randomization in Auditing Differentially Private ML](https://mlsanity.com/paper/2305.18447/) (2023)
- [The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text](https://mlsanity.com/paper/2502.14921/) (2025)
- [Detecting Violations of Differential Privacy for Quantum Algorithms](https://mlsanity.com/paper/2309.04819/) (2023)
- [Towards A Hybrid Quantum Differential Privacy](https://mlsanity.com/paper/2501.07844/) (2025)
- [Quantum Convolutional Neural Network: A Hybrid Quantum-Classical Approach for Iris Dataset Classification](https://mlsanity.com/paper/2410.16344/) (2024)
- [Modeling Quantum Machine Learning for Genomic Data Analysis](https://mlsanity.com/paper/2501.08193/) (2025)

## Abstract (arXiv)

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.