arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.11486cs.CReess.SP
收藏

增强隐私的空中联邦学习

Over-the-Air Federated Learning with Enhanced Privacy

Xiaochan Xue, Moh Khalid Hasan, Shucheng Yu, Laxima Niure Kandel, Min Song

摘要:

联邦学习(FL)已经成为一种很有前途的学习范式,其中只有局部模型参数(梯度)是共享的。私人用户数据永远不会离开本地设备,从而保护数据隐私。然而,最近的研究表明,即使用户从不共享本地数据,在没有保护的情况下交换模型参数也会泄露私人信息。此外,在无线系统中,模型参数的频繁传输会造成巨大的带宽消耗和网络拥塞时,模型是大的。为了解决这个问题,我们提出了一个新的FL框架,有效的空中参数聚合和强大的隐私保护的用户数据和模型。我们通过在终端设备上引入成对可消除的随机人工噪声(PCR-AN)来实现这一点。与现有的基于空中计算(AirComp)的FL方案相比,我们的设计提供了更强的隐私保护。我们分析了所提出的无线FL聚合算法的保密能力和收敛速度。

英文摘要:

Federated learning (FL) has emerged as a promising learning paradigm in which only local model parameters (gradients) are shared. Private user data never leaves the local devices thus preserving data privacy. However, recent research has shown that even when local data is never shared by a user, exchanging model parameters without protection can also leak private information. Moreover, in wireless systems, the frequent transmission of model parameters can cause tremendous bandwidth consumption and network congestion when the model is large. To address this problem, we propose a new FL framework with efficient over-the-air parameter aggregation and strong privacy protection of both user data and models. We achieve this by introducing pairwise cancellable random artificial noises (PCR-ANs) on end devices. As compared to existing over-the-air computation (AirComp) based FL schemes, our design provides stronger privacy protection. We analytically show the secrecy capacity and the convergence rate of the proposed wireless FL aggregation algorithm.

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。

↑