Experimentally validated quantum-secure federated learning over a multi-user quantum network

Abstract

Federated learning enables decentralized, privacy-preserving training but remains vulnerable to privacy leakage in the quantum era. Quantum federated learning (QFL) offers a promising path towards enhanced security and efficiency. However, a practical and experimentally validated QFL protocol utilizing near-term quantum techniques to address data privacy has been lacking. Here we present QuNetQFL, a QFL protocol implemented on quantum networks, in which local model updates are masked with distributed quantum secret keys, offering information-theoretic security during aggregation. We experimentally validate the protocol on a four-client quantum network and benchmark its performance using the generated keys on quantum and real-world datasets. Adding a single quantum client significantly improves global accuracy for classifying multipartite entangled and non-stabilizer quantum datasets. For language tasks, we apply QuNetQFL to sentiment analysis by federated fine-tuning of a hybrid classical-quantum language model, achieving comparable and robust performance in simulation and on real quantum hardware. Large-scale simulations further demonstrate scalability to 200 clients for handwritten-digit recognition, with rapid convergence and a $75\%$ reduction in communication cost via model compression. Our work establishes a practical and scalable route to quantum-secure federated learning for the emerging quantum internet.

25 pages, 7 figures, 7 tables, Accepted by Research

References in corpus (34)

• Quantum Machine Learning
• Variational Quantum Algorithms
• The Future of Digital Health with Federated Learning
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Measurement-device-independent quantum key distribution
• Overcoming the rate-distance barrier of quantum key distribution without using quantum repeaters
• Challenges and Opportunities in Quantum Machine Learning
• Quantum repeaters: From quantum networks to the quantum internet
• Application of a resource theory for magic states to fault-tolerant quantum computing
• Experimental Twin-Field Quantum Key Distribution Over 1000 km Fiber Distance
• Qubit teleportation between non-neighboring nodes in a quantum network
• Entanglement Certification $-$ From Theory to Experiment
• Robust data encodings for quantum classifiers
• Stabilizer Rényi entropy
• A Quantum-Logic Gate between Distant Quantum-Network Modules
• Experimental Quantum Communication Overcomes the Rate-loss Limit without Global Phase Tracking
• Quantifying the magic of quantum channels
• Experimental measurement-device-independent type quantum key distribution with flawed and correlated sources
• Quantum federated learning through blind quantum computing
• QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer
• Towards provably efficient quantum algorithms for large-scale machine-learning models
• Quantum Neural Network for Quantum Neural Computing
• Experimental quantum e-commerce
• Demonstration of quantum-digital payments
• Non-IID Quantum Federated Learning with One-shot Communication Complexity
• Multi-client distributed blind quantum computation with the Qline architecture
• Experimental Quantum Byzantine Agreement on a Three-User Quantum Network with Integrated Photonics
• Quantum Data Center: Perspectives
• Experimental Efficient Source-Independent Quantum Secret Sharing against Coherent Attacks
• Blind quantum machine learning with quantum bipartite correlator
• Experimental Coherent One-Way Quantum Key Distribution with Simplicity and Practical Security
• Quantum delegated and federated learning via quantum homomorphic encryption
• Experimental Efficient Source-Independent Quantum Conference Key Agreement
• QSteed: A Resource-Virtualized and Hardware-Aware Quantum Compilation Framework for Real Quantum Computing Processors