发表机构
Université Paris-Saclay; CEA; CNRGH（巴黎-萨克雷大学; 法国原子能和替代能源委员会; 国家人类基因组研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对联邦学习在医疗保健和基因组学等领域的安全隐私挑战，提出MOSAIC-FL框架，集成gRPC通信层等，用CKKS同态加密系统变体实现盲模型聚合，经多种用例验证其有效性，能确保安全并减轻密钥恢复攻击。
AI 中文摘要
安全和隐私是联邦学习（FL）的首要要求，特别是在医疗保健和基因组学等必须分析敏感信息的领域。我们的FL框架旨在应对这些挑战，同时提出一种模块化、灵活的微服务架构。具体而言，它集成了高效的gRPC通信层和有限状态机，以确保强大的组件同步和威胁检测，同时依赖使用CKKS同态加密系统阈值变体的容错安全聚合协议。这允许编排服务器进行盲模型聚合，解密需要至少N个中的t个活跃客户端，同时由于加密和网络协议而最小化通信开销。我们通过噪声泛洪确保IND-CPA-D安全性，并通过每轮更新集体密钥材料来减轻对同步解密器的近期密钥恢复攻击。我们通过从标准图像识别（EMNIST）到复杂基因组分类（包括TCGA上的乳腺癌亚型分类）的各种用例来证明该框架的有效性，评估不同阈值和模型规模下的系统性能。
英文摘要
Security and privacy are primordial requirements for Federated Learning (FL), especially in fields such as healthcare and genomics where sensitive information has to be analyzed. Our FL framework is designed to address these challenges while proposing a modular, flexible and micro-service architecture. More precisely, it integrates an efficient gRPC communication layer and a Finite State Machine to ensure robust component synchronization and threat detection, while relying on a fault-tolerant secure aggregation protocol using a Threshold variant of the CKKS homomorphic cryptosystem. This allows blind model aggregation by an orchestration server, requiring a minimum of $t$-out-of-$N$ active clients for decryption while minimizing communication overhead thanks to both cryptographic and network protocols. We ensure IND-CPA-D security through noise flooding and mitigate the recent key-recovery attack on synchronized decryptors by renewing the collective key material at every round. We demonstrate the framework's effectiveness through diverse use cases, ranging from standard image recognition (EMNIST) to complex genomic classification including breast cancer subtyping on TCGA, evaluating system performance across different threshold values and model scales.
Comments8 pages, 4 figures, 2 tables. Accepted and presented at SECRYPT 2026, 23rd International Conference on Security and Cryptography, Porto, Portugal, 16-18 July 2026. https://secrypt.scitevents.org
