Quantum Key Distribution Secured Federated Learning for Channel Estimation and Radar Spectrum Sensing in 6G Networks
This addresses security vulnerabilities in federated learning for 6G wireless networks, though it appears incremental by combining existing techniques.
This paper tackles secure federated learning for 6G networks by combining quantum key distribution with federated learning to protect model updates during training for channel estimation and radar spectrum sensing, achieving NMSE of 0.216 for channel estimation and 92.1% accuracy with 0.72 mIoU for radar sensing while preventing eavesdropping.
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.