用量子密钥保护联邦学习，防窃听同时完成6G信道与雷达感知。
Quantum Key Distribution Secured Federated Learning for Channel Estimation and Radar Spectrum Sensing in 6G Networks
- 用量子密钥+掩码上传模型更新，服务器看不到原始参数。
- 信道估计NMSE达0.216，雷达感知准确率92.1%，mIoU为0.72。
- 遭窃听时自动中止，密钥泄露可被检测，聚合结果仍精准。
本文提出一种基于量子密钥分发（QKD）的联邦学习框架，用于下一代网络（NextG/Beyond 6G）中的无线信道估计与雷达频谱感知。采用BB84协议抽象和成对加性掩码机制，客户端（使用CNN进行信道估计，U-Net进行雷达分割）仅上传掩码后的模型更新，服务器聚合时不接触明文参数；无QKD密钥的窃听者无法恢复个体更新。实验表明，安全联邦学习在信道估计上达到0.216的归一化均方误差（NMSE），雷达感知准确率为92.1%，交并比（mIoU）为0.72。当存在窃听时，量子误码率（QBER）升至约25%，所有训练轮次按设计中止；重构误差保持在10⁻⁵以下，证实聚合正确性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。