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

TL;DR

This paper demonstrates the first practical implementation of perfectly-secure quantum homomorphic encryption for quantum neural networks, enabling secure federated training and private inference in quantum machine learning.

Contribution

It introduces a realistic scheme for quantum homomorphic encryption applied to quantum neural networks, supporting secure multi-party quantum machine learning tasks.

Findings

Implemented quantum convolutional neural networks using Clifford+$T$ decomposition.

Enabled secure federated training and private inference with encrypted quantum data.

Revealed probabilistic model protection through Pauli gate concealment.

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.