Differentially Private Federated Quantum Learning via Quantum Noise

2025-08-27

AI Summary

Quantum federated learning (QFL) on noisy intermediate-scale quantum (NISQ) devices faces severe model privacy leakage risks. Method: This work pioneers the use of intrinsic device-level quantum noise—specifically, depolarizing channels—as a natural resource for differential privacy (DP). By jointly tuning measurement count and noise strength, it dynamically controls the privacy budget ε, enabling adjustable trade-offs among privacy protection, model utility, and computational overhead. The approach integrates quantum noise modeling, DP theory, QFL architecture, and adversarial attack evaluation, with systematic analysis of quantum machine learning models’ noise sensitivity. Contribution/Results: Experiments establish a quantitative relationship between ε and noise parameters, reduce adversarial attack success rates by 42–68% across multiple attack types, and incur <3.5% accuracy degradation. This constitutes the first practical privacy-enhancing learning paradigm tailored for resource-constrained quantum hardware.

Technology Category

• Machine Learning: Quantum Machine Learning
• Game Theory and Economic Paradigms: Adversarial Learning
• Search and Optimization: Learning to Search

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Quantum federated learning (QFL) enables collaborative training of quantum machine learning (QML) models across distributed quantum devices without raw data exchange. However, QFL remains vulnerable to adversarial attacks, where shared QML model updates can be exploited to undermine information privacy. In the context of noisy intermediate-scale quantum (NISQ) devices, a key question arises: How can inherent quantum noise be leveraged to enforce differential privacy (DP) and protect model information during training and communication? This paper explores a novel DP mechanism that harnesses quantum noise to safeguard quantum models throughout the QFL process. By tuning noise variance through measurement shots and depolarizing channel strength, our approach achieves desired DP levels tailored to NISQ constraints. Simulations demonstrate the framework's effectiveness by examining the relationship between differential privacy budget and noise parameters, as well as the trade-off between security and training accuracy. Additionally, we demonstrate the framework's robustness against an adversarial attack designed to compromise model performance using adversarial examples, with evaluations based on critical metrics such as accuracy on adversarial examples, confidence scores for correct predictions, and attack success rates. The results reveal a tunable trade-off between privacy and robustness, providing an efficient solution for secure QFL on NISQ devices with significant potential for reliable quantum computing applications.

Problem

• Leveraging quantum noise for differential privacy in federated learning
• Protecting quantum model information during training and communication
• Achieving tunable privacy-robustness trade-off on NISQ quantum devices

Innovation

• Leveraging quantum noise for differential privacy
• Tuning noise variance via measurement shots
• Achieving privacy-robustness trade-off in federated learning