Saved in:
Bibliographic Details
Main Authors: Ortega, Sergio A., Martin-Delgado, Miguel A.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.12712
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908837209964544
author Ortega, Sergio A.
Martin-Delgado, Miguel A.
author_facet Ortega, Sergio A.
Martin-Delgado, Miguel A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12712
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reverse Delegated Training and Private Inference via Perfectly-Secure Quantum Homomorphic Encryption
Ortega, Sergio A.
Martin-Delgado, Miguel A.
Quantum Physics
Neural and Evolutionary Computing
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.
title Reverse Delegated Training and Private Inference via Perfectly-Secure Quantum Homomorphic Encryption
topic Quantum Physics
Neural and Evolutionary Computing
url https://arxiv.org/abs/2602.12712