Quantum Key Distribution Secured Federated Learning for Channel Estimation and Radar Spectrum Sensing in 6G Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Catak, Ferhat Ozgur, Kuzlu, Murat, Seo, Jungwon, Cali, Umit
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912969152004096
author Catak, Ferhat Ozgur
Kuzlu, Murat
Seo, Jungwon
Cali, Umit
author_facet Catak, Ferhat Ozgur
Kuzlu, Murat
Seo, Jungwon
Cali, Umit
contents This paper presents a federated learning framework secured by quantum key distribution (QKD) for wireless channel estimation and radar spectrum sensing in the next generation networks (NextG or Beyond 6G). A BB84-style protocol abstraction and pairwise additive masking are utilized to train clients' local models (CNN for channel estimation, U-Net for radar segmentation) and upload only masked model updates. The server aggregates without observing plain parameters; an eavesdropper without QKD keys cannot recover individual updates. Experiments show that secure FL achieves NMSE of 0.216 for channel estimation and 92.1\% accuracy with 0.72 mIoU for radar sensing. When an eavesdropper is present, QBER rises to $\sim$25\% and all rounds abort as intended; reconstruction error remains below $10^{-5}$, confirming correct aggregation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15649
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Quantum Key Distribution Secured Federated Learning for Channel Estimation and Radar Spectrum Sensing in 6G Networks
Catak, Ferhat Ozgur
Kuzlu, Murat
Seo, Jungwon
Cali, Umit
Cryptography and Security
Information Theory
Machine Learning
This paper presents a federated learning framework secured by quantum key distribution (QKD) for wireless channel estimation and radar spectrum sensing in the next generation networks (NextG or Beyond 6G). A BB84-style protocol abstraction and pairwise additive masking are utilized to train clients' local models (CNN for channel estimation, U-Net for radar segmentation) and upload only masked model updates. The server aggregates without observing plain parameters; an eavesdropper without QKD keys cannot recover individual updates. Experiments show that secure FL achieves NMSE of 0.216 for channel estimation and 92.1\% accuracy with 0.72 mIoU for radar sensing. When an eavesdropper is present, QBER rises to $\sim$25\% and all rounds abort as intended; reconstruction error remains below $10^{-5}$, confirming correct aggregation.
title Quantum Key Distribution Secured Federated Learning for Channel Estimation and Radar Spectrum Sensing in 6G Networks
topic Cryptography and Security
Information Theory
Machine Learning
url https://arxiv.org/abs/2603.15649