Guaranteeing Privacy in Hybrid Quantum Learning through Theoretical Mechanisms

ICLR 2026 Conference Submission13180 Authors

Keywords: differential privacy, privacy amplification, quantum machine learning, quantum noise, adversarial robustness

Abstract: Quantum Machine Learning (QML) is becoming increasingly prevalent due to its potential to enhance classical machine learning (ML) tasks, such as classification. Although quantum noise is often viewed as a major challenge in quantum computing, it also offers a unique opportunity to enhance privacy. In particular, quantum noise can serve as a natural source of randomness that reduces the need for additional classical noise without compromising the privacy budget while potentially improving model utility. However, the integration of classical and quantum noise for privacy preservation remains unexplored. In this work, we propose a hybrid noise-added mechanism, HYPER-Q, that combines classical and quantum noise to protect the privacy of QML models. We provide a comprehensive analysis of its privacy guarantees and establish theoretical bounds on its utility. Empirically, we demonstrate that HYPER-Q outperforms existing classical noise-based mechanisms in terms of adversarial robustness across multiple real-world datasets.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 13180