arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.00974cs.CRcs.AI
收藏

增强联邦学习中的隐私保护:面向真实世界医疗应用的安全聚合

Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications

Inria(法国国家信息与自动化研究所);EURECOM(欧洲数字与网络研究中心);Université Côte d’Azur(蔚蓝海岸大学)

Riccardo Taiello, Sergen Cansiz, Marc Vesin, Francesco Cremonesi, Lucia Innocenti, Melek Önen, Marco Lorenzi

AI总结:

本文在 Fed-BioMed 框架中实现并比较 JL 和 LOM 两种安全聚合协议,通过四个医疗数据集的实验证明其能在几乎不影响准确率的前提下有效保护隐私,验证了安全聚合在真实医疗场景中的可行性。

摘要:

在真实世界场景中部署联邦学习(FL),尤其是在医疗领域,面临着通信和安全方面的挑战。特别是,就联邦聚合过程而言,研究人员一直专注于研究安全聚合(SA)方案,以对客户端传输的模型参数提供隐私保证。然而,由于计算和通信瓶颈,SA 在当前可用的 FL 框架中的实际可用性目前仍然有限。为填补这一空白,本研究探索了在开源 Fed-BioMed 框架内实现 SA。我们实现并比较了两种 SA 协议,即 Joye-Libert(JL)和 Low Overhead Masking(LOM),并在一组医疗数据分析问题中提供了广泛的基准测试。我们在四个数据集上的理论和实验评估表明,SA 协议能够在保持任务准确率的同时有效保护隐私。训练期间的计算开销在 CPU 上低于 1%,在 GPU 上对于大型模型低于 50%,保护阶段耗时少于 10 秒。将 SA 纳入 Fed-BioMed 对任务准确率的影响相比非 SA 场景不超过 2%。总体而言,本研究证明了 SA 在真实世界医疗应用中的可行性,并有助于缩小在敏感应用中采用隐私保护技术的差距。

英文摘要:

Deploying federated learning (FL) in real-world scenarios, particularly in healthcare, poses challenges in communication and security. In particular, with respect to the federated aggregation procedure, researchers have been focusing on the study of secure aggregation (SA) schemes to provide privacy guarantees over the model's parameters transmitted by the clients. Nevertheless, the practical availability of SA in currently available FL frameworks is currently limited, due to computational and communication bottlenecks. To fill this gap, this study explores the implementation of SA within the open-source Fed-BioMed framework. We implement and compare two SA protocols, Joye-Libert (JL) and Low Overhead Masking (LOM), by providing extensive benchmarks in a panel of healthcare data analysis problems. Our theoretical and experimental evaluations on four datasets demonstrate that SA protocols effectively protect privacy while maintaining task accuracy. Computational overhead during training is less than 1% on a CPU and less than 50% on a GPU for large models, with protection phases taking less than 10 seconds. Incorporating SA into Fed-BioMed impacts task accuracy by no more than 2% compared to non-SA scenarios. Overall this study demonstrates the feasibility of SA in real-world healthcare applications and contributes in reducing the gap towards the adoption of privacy-preserving technologies in sensitive applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑