Privacy-preserving quantum federated learning via gradient hiding

Abstract

Distributed quantum computing, particularly distributed quantum machine learning, has gained substantial prominence for its capacity to harness the collective power of distributed quantum resources, transcending the limitations of individual quantum nodes. Meanwhile, the critical concern of privacy within distributed computing protocols remains a significant challenge, particularly in standard classical federated learning (FL) scenarios where data of participating clients is susceptible to leakage via gradient inversion attacks by the server. This paper presents innovative quantum protocols with quantum communication designed to address the FL problem, strengthen privacy measures, and optimize communication efficiency. In contrast to previous works that leverage expressive variational quantum circuits or differential privacy techniques, we consider gradient information concealment using quantum states and propose two distinct FL protocols, one based on private inner-product estimation and the other on incremental learning. These protocols offer substantial advancements in privacy preservation with low communication resources, forging a path toward efficient quantum communication-assisted FL protocols and contributing to the development of secure distributed quantum machine learning, thus addressing critical privacy concerns in the quantum computing era.

arXiv comment12 pages, 2 figures, 1 table

References in corpus (27)

• Quantum Cryptography
• Deep Learning with Differential Privacy
• Quantum cryptography: Public key distribution and coin tossing
• Decoy State Quantum Key Distribution
• Secure quantum key distribution with realistic devices
• Quantum fingerprinting
• Parameterized quantum circuits as machine learning models
• Quantum Internet: Networking Challenges in Distributed Quantum Computing
• Universal blind quantum computation
• iDLG: Improved Deep Leakage from Gradients
• Deterministic teleportation of a quantum gate between two logical qubits
• Towards a Distributed Quantum Computing Ecosystem
• Efficient Distributed Quantum Computing
• Exponential Communication Complexity Advantage from Quantum Superposition of the Direction of Communication
• Quantum noise protects quantum classifiers against adversaries
• Quantum gate teleportation between separated qubits in a trapped-ion processor
• Evaluating Gradient Inversion Attacks and Defenses in Federated Learning
• Quantum federated learning through blind quantum computing
• Beyond the swap test: optimal estimation of quantum state overlap
• Multi-client distributed blind quantum computation with the Qline architecture
• Federated Learning with Quantum Secure Aggregation
• Towards Quantum Federated Learning
• Blind quantum machine learning with quantum bipartite correlator
• Communication-efficient Quantum Algorithm for Distributed Machine Learning
• Expressive variational quantum circuits provide inherent privacy in federated learning
• Exponential Quantum Communication Advantage in Distributed Inference and Learning
• Enhancing Privacy against Inversion Attacks in Federated Learning by using Mixing Gradients Strategies

Cited by in corpus (5)

• Quantum Cloud Computing: Trends and Challenges
• Quantum-Inspired Privacy-Preserving Federated Learning Framework for Secure Dementia Classification
• Blind quantum machine learning with quantum bipartite correlator
• When Federated Learning Meets Quantum Computing: Survey and Research Opportunities
• Quantum delegated and federated learning via quantum homomorphic encryption