发表机构
University of Trento; Huawei Technologies Duesseldorf; Universidad Politécnica de Madrid（特伦托大学; 华为技术杜塞尔多夫有限公司; 马德里理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出一种集成冻结骨干、知识蒸馏与量化的联邦学习框架，在真实物理密钥分配测试平台上将密钥使用量减少约35倍，同时保持预测精度，从而解决信息论安全密钥交换的吞吐量瓶颈，实现可持续的联邦学习训练。
AI 中文摘要
联邦学习（FL）使得各机构能够在无需集中敏感数据的情况下协作训练模型，非常适合医学影像等注重隐私的应用。为在安全聚合过程中保护联邦学习模型更新，通常采用加性掩码技术。然而，其底层经典密钥建立仅具有计算安全性。另一方面，基于物理的信息论安全（ITS）密钥交换引入了实际约束：有限的密钥生成速率和限时存储严重限制了吞吐量及未压缩模型的持续训练。在本工作中，我们通过开发一个集成冻结骨干网络、知识蒸馏和量化的联邦学习框架来解决这一瓶颈。这些技术减少了通信负载，从而降低了密钥材料消耗。超越模拟，我们在一个涉及胸部X射线分类应用的真实物理密钥分配测试平台上对该框架进行了基准测试。结果表明，在保持预测精度的同时，密钥使用量可减少约35倍。这防止了缓冲区耗尽和密钥过期，使得在物理密钥生成约束下可持续进行联邦学习训练。
英文摘要
Federated Learning (FL) enables collaborative training of models across institutions without centralizing sensitive data, making it well-suited for privacy-concerned applications, such as medical imaging. To protect FL model updates during secure aggregation, additive masking is commonly employed. However, its underlying classical key establishment is only computationally secure. On the other hand, physics-based Information-Theoretically Secure (ITS) key exchange introduces practical constraints: finite key generation rates and time-limited storage severely limit throughput and sustained training of uncompressed models. In this work, we address this bottleneck by developing an FL framework that integrates frozen backbones, knowledge distillation, and quantization. These techniques reduce communication payload and, consequently, key material consumption. Moving beyond simulation, we benchmark this framework on a real physics-based key distribution testbed involving a chest X-ray classification application. Our results show that key usage can be reduced by $\sim$35$\times$ while maintaining predictive accuracy. This prevents buffer depletion and key expiration, enabling sustainable FL training under physical key generation constraints.
Comments6 pages. Accepted at Federated Intelligence and Digital Twins for Autonomous Systems and IoT Workshop (FIDTA 2026), co-located with ACM MobiHoc 2026
