Reverse Delegated Training and Private Inference via Perfectly-Secure Quantum Homomorphic Encryption

2026-02-13

AI Summary

This work addresses the challenge of enabling quantum machine learning in cloud environments while preserving data privacy and leveraging remote computational resources. It presents the first application of perfectly secure quantum homomorphic encryption (QHE) to quantum convolutional neural networks, achieving efficient computation through Clifford+T circuit decomposition. The authors introduce a reverse-delegation training mechanism to support collaborative multi-party scenarios and employ Pauli gate randomization to conceal model parameters, thereby ensuring joint privacy of both data and models. The proposed framework simultaneously enables private inference and secure training, demonstrating the practical feasibility of QHE in real-world quantum machine learning applications and establishing a new paradigm for secure multi-party quantum learning.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Quantum machine learning in cloud environments requires protecting sensitive data while enabling remote computation. Here we demonstrate the first realistic implementations of a perfectly-secure quantum homomorphic encryption (QHE) scheme applied to quantum neural networks (QNN). Using efficient Clifford+$T$ decomposition, we implement quantum convolutional neural networks for two complementary scenarios: (i) reverse delegated training, where encrypted data from multiple providers trains a user's network via federated aggregation; (ii) private inference, where users process encrypted data with remote quantum networks. Moreover, analysis of server circuit privacy reveals probabilistic model protection through Pauli gate concealment. These results establish perfectly-secure QHE as a practical framework for multi-party quantum machine learning.

Problem

• quantum homomorphic encryption
• private inference
• reverse delegated training
• quantum machine learning
• data privacy

Innovation

• Quantum Homomorphic Encryption
• Quantum Neural Networks
• Reverse Delegated Training
• Private Inference
• Clifford+T Decomposition