Quantum federated learning through blind quantum computing

Abstract

Private distributed learning studies the problem of how multiple distributed entities collaboratively train a shared deep network with their private data unrevealed. With the security provided by the protocols of blind quantum computation, the cooperation between quantum physics and machine learning may lead to unparalleled prospect for solving private distributed learning tasks. In this paper, we introduce a quantum protocol for distributed learning that is able to utilize the computational power of the remote quantum servers while keeping the private data safe. For concreteness, we first introduce a protocol for private single-party delegated training of variational quantum classifiers based on blind quantum computing and then extend this protocol to multiparty private distributed learning incorporated with differential privacy. We carry out extensive numerical simulations with different real-life datasets and encoding strategies to benchmark the effectiveness of our protocol. We find that our protocol is robust to experimental imperfections and is secure under the gradient attack after the incorporation of differential privacy. Our results show the potential for handling computationally expensive distributed learning tasks with privacy guarantees, thus providing a valuable guide for exploring quantum advantages from the security perspective in the field of machine learning with real-life applications.

arXiv comment6.5 pages (main text) + 4 pages (supplementary materials), 12 figures

References in corpus (33)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Quantum Machine Learning
• Quantum algorithm for solving linear systems of equations
• Federated Learning: Strategies for Improving Communication Efficiency
• Supervised learning with quantum enhanced feature spaces
• Machine learning and the physical sciences
• Quantum computational advantage using photons
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Quantum principal component analysis
• Evaluating analytic gradients on quantum hardware
• Quantum generative adversarial learning
• Experimental Demonstration of Blind Quantum Computing
• Quantum-state preparation with universal gate decompositions
• Hybrid Quantum-Classical Approach to Quantum Optimal Control
• Unconditionally verifiable blind computation
• Quantum generative adversarial learning in a superconducting quantum circuit
• Quantum circuits with uniformly controlled one-qubit gates
• Quantum noise protects quantum classifiers against adversaries
• Machine learning meets quantum physics
• Suppression of photon shot noise dephasing in a tunable coupling superconducting qubit
• Quantum Adversarial Machine Learning
• Experimental Blind Quantum Computing for a Classical Client
• Efficient universal blind computation
• Secure entanglement distillation for double-server blind quantum computation
• Adequacy of Si:P Chains as Fermi-Hubbard Simulators
• Blind quantum computation with noise environment
• InstaHide: Instance-hiding Schemes for Private Distributed Learning
• Secure assisted quantum computation

Cited by in corpus (20)

• Recent advances for quantum classifiers
• FedQNN: Federated Learning using Quantum Neural Networks
• High Dimensional Quantum Machine Learning With Small Quantum Computers
• Non-IID Quantum Federated Learning with One-shot Communication Complexity
• Multi-client distributed blind quantum computation with the Qline architecture
• QFNN-FFD: Quantum Federated Neural Network for Financial Fraud Detection
• Quantum Capsule Networks
• How quantum computing can enhance biomarker discovery
• Privacy-preserving quantum federated learning via gradient hiding
• A Privacy-Preserving Federated Framework with Hybrid Quantum-Enhanced Learning for Financial Fraud Detection
• Blind quantum machine learning with quantum bipartite correlator
• Photonic kernel machine learning for ultrafast spectral analysis
• When Federated Learning Meets Quantum Computing: Survey and Research Opportunities
• Entanglement-induced provable and robust quantum learning advantages
• Quantum-machine-assisted Drug Discovery
• Variational secure cloud quantum computing
• Hardware requirements for trapped-ion based verifiable blind quantum computing with a measurement-only client
• Quantum delegated and federated learning via quantum homomorphic encryption
• Experimentally validated quantum-secure federated learning over a multi-user quantum network
• Verifiable cloud-based variational quantum algorithms