Distributed and Secure Kernel-Based Quantum Machine Learning

2024-08-16

arXiv.org

AI Summary

This work addresses secure quantum computation of classical kernel functions—specifically polynomial, RBF, and Laplacian kernels—in distributed data settings. Methodologically, it integrates quantum feature mapping with quantum teleportation protocols to achieve privacy preservation and computational integrity under a trustless assumption, while designing a low-communication-complexity distributed quantum protocol that avoids scaling communication overhead with data size. The framework is validated on the Qiskit Aer simulator and multiple public datasets, demonstrating correctness, security, and scalability of kernel evaluation. Its primary contribution is the first scalable, low-communication, trust-free quantum kernel learning paradigm, providing a practical pathway for privacy-sensitive quantum machine learning applications.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Distributed Search
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Semantics and Knowledge: Provenance, trust, security and privacy, and ethical issues in managing semantic data

Abstract

Quantum computing promises to revolutionize machine learning, offering significant efficiency gains in tasks such as clustering and distance estimation. Additionally, it provides enhanced security through fundamental principles like the measurement postulate and the no-cloning theorem, enabling secure protocols such as quantum teleportation and quantum key distribution. While advancements in secure quantum machine learning are notable, the development of secure and distributed quantum analogues of kernel-based machine learning techniques remains underexplored. In this work, we present a novel approach for securely computing common kernels, including polynomial, radial basis function (RBF), and Laplacian kernels, when data is distributed, using quantum feature maps. Our methodology introduces a robust framework that leverages quantum teleportation to ensure secure and distributed kernel learning. The proposed architecture is validated using IBM's Qiskit Aer Simulator on various public datasets.

Problem

• Develop secure distributed quantum kernel methods
• Leverage quantum feature maps for kernel computation
• Ensure security via quantum teleportation protocols

Innovation

• Quantum feature maps for secure kernel computation
• Leverages quantum teleportation for secure learning
• Validated using IBM Qiskit Aer Simulator