Quantum delegated and federated learning via quantum homomorphic encryption

Abstract

Quantum learning models hold the potential to bring computational advantages over the classical realm. As powerful quantum servers become available on the cloud, ensuring the protection of clients' private data becomes crucial. By incorporating quantum homomorphic encryption schemes, we present a general framework that enables quantum delegated and federated learning with a computation-theoretical data privacy guarantee. We show that learning and inference under this framework feature substantially lower communication complexity compared with schemes based on blind quantum computing. In addition, in the proposed quantum federated learning scenario, there is less computational burden on local quantum devices from the client side, since the server can operate on encrypted quantum data without extracting any information. We further prove that certain quantum speedups in supervised learning carry over to private delegated learning scenarios employing quantum kernel methods. Our results provide a valuable guide toward privacy-guaranteed quantum learning on the cloud, which may benefit future studies and security-related applications.

arXiv comment5 pages, 1 figure, 1 table

References in corpus (29)

• Deep Learning with Differential Privacy
• Quantum Machine Learning
• Variational Quantum Algorithms
• Quantum support vector machine for big data classification
• Quantum Circuit Learning
• Quantum Error Correction for Quantum Memories
• Evaluating analytic gradients on quantum hardware
• Challenges and Opportunities in Quantum Machine Learning
• Quantum advantage in learning from experiments
• A rigorous and robust quantum speed-up in supervised machine learning
• Universal blind quantum computation
• Quantum computing on encrypted data
• Machine learning meets quantum physics
• Blind topological measurement-based quantum computation
• Quantum federated learning through blind quantum computing
• Quantum homomorphic encryption for circuits of low $T$-gate complexity
• Robustness and device independence of verifiable blind quantum computing
• On the Quantum versus Classical Learnability of Discrete Distributions
• Enhancing Generative Models via Quantum Correlations
• Quantum homomorphic encryption from quantum codes
• Shadows of quantum machine learning
• Non-IID Quantum Federated Learning with One-shot Communication Complexity
• Fault-tolerant Operations for Universal Blind Quantum Computation
• Privacy-preserving quantum federated learning via gradient hiding
• Experimental Demonstration of Quantum Fully Homomorphic Encryption with Application in a Two-Party Secure Protocol
• Quantum Data Center: Perspectives
• Statistical Complexity of Quantum Learning
• Blind quantum machine learning with quantum bipartite correlator
• Quantum Fully Homomorphic Encryption by Integrating Pauli One-time Pad with Quaternions

Cited by in corpus (1)

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