Privacy Preserving Distributed QML with QKD-Aware Scheduling for Quantum Networks
Year: 2026
Type: conference-paper
Abstract: This work introduces a novel distributed Quantum Machine Learning (QML) scheme that integrates differential privacy methods to enable secure and efficient classification. The approach begins with the computation of an embedding that, given a seed, is randomly segmented into multiple sub-vectors. Each segment is perturbed with noise to enforce differential privacy and is then reduced in dimensionality via Principal Component Analysis (PCA). This PCA addresses the parameter limitations of QML. The reduced embeddings are distributed to multiple QML centers, where they are processed by a QML classifier. To obtain a final prediction, individual decisions from each center are combined through an aggregation mechanism. All classical information communications between the server and QML centers are encrypted and protected by a Quantum Key Distribution (QKD) network between these nodes. This scheme enables training and inference in distributed QML settings while robustly preserving privacy. Empirical evaluations show that the method maintains competitive accuracy with fewer quantum resources, paving the way for practical and scalable deployments of QML in real-world quantum computing context.
Institution: Universidad de La Laguna
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7163999953