In this paper, a novel secure and private over-the-air federated learning (SP-OTA-FL) framework is studied where noise is employed to protect data privacy and system security. Specifically, the privacy leakage of user data and the security level of the system are measured by differential privacy (DP) and mean square error security (MSE-security), respectively. To mitigate the impact of noise on learning accuracy, we propose a channel-weighted post-processing (CWPP) mechanism, which assigns a smaller weight to the gradient of the device with poor channel conditions. Furthermore, employing CWPP can avoid the issue that the signal-to-noise ratio (SNR) of the overall system is limited by the device with the worst channel condition in aligned over-the-air federated learning (OTA-FL). We theoretically analyze the effect of noise on privacy and security protection and also illustrate the adverse impact of noise on learning performance by conducting convergence analysis. Based on these analytical results, we propose device scheduling policies considering privacy and security protection in different cases of channel noise. In particular, we formulate an integer nonlinear fractional programming problem aiming to minimize the negative impact of noise on the learning process. We obtain the closed-form solution to the optimization problem when the model is with high dimension. For the general case, we propose a secure and private algorithm (SPA) based on the branch-and-bound (BnB) method, which can obtain an optimal solution with low complexity. The effectiveness of the proposed CWPP mechanism and the policies for device selection are validated through simulations.
Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search
Brandeis University(布兰迪斯大学);Northeastern University(东北大学);Beihang University(北京航空航天大学);Shenzhen Research Institute of Big Data(深圳大数据研究院);Zhejiang University(浙江大学);University of Windsor(温莎大学)
Communication-Learning Co-Design for Differentially Private Over-the-Air Federated Distillation
Department of Information Engineering, The Chinese University of Hong Kong(信息工程系,香港中文大学);Intelligent Transportation Thrust, The Hong Kong University of Science and Technology (Guangzhou)(智能交通研究组,香港科学与技术大学(广州))
NCAirFL: CSI-Free Over-the-Air Federated Learning Based on Non-Coherent Detection
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Arizona State University(亚利桑那州立大学);The Hong Kong University of Science and Technology(香港科技大学)
ShanghaiTech University(上海科技大学);Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences(中国科学院上海微系统与信息技术研究所);University of Chinese Academy of Sciences(中国科学院大学)
On the Convergence of Differentially Private Federated Learning on Non-Lipschitz Objectives, and with Normalized Client Updates
University of Texas at Austin(德克萨斯大学奥斯汀分校);Purdue University(普渡大学)
对于具有非Lipschitz目标函数的差分私有联邦学习(FL)(即,当梯度范数没有界时)。其主要原因是裁剪操作(即,投影到固定半径的$\ell_2$球上,称为剪切阈值),用于限制平均更新对每个客户端更新的灵敏度,这引入了偏差,这取决于剪切阈值和FL中的局部步骤的数量,并且分析这一点并不容易。对于Lipschitz函数,Lipschitz常数用作具有零偏差的平凡限幅阈值。然而,Lipschitz性在许多实际情况下并不成立;此外,验证它和计算Lipschitz常数是困难的。因此,限幅阈值的选择是重要的,并且在实践中需要大量的调谐。在本文中,我们提供了第一个收敛结果,私人FL光滑\textit{convex}目标\textit{for a general clipping threshold} - \textit{without assuming Lipschitzness}。我们还研究了一种更简单的裁剪(用于边界敏感性)替代方案,即\textit{normalization} --在这种情况下,我们只使用客户端更新中的单位向量的缩放版本,完全丢弃幅度信息。{The理论上证明了基于归一化的私有FL算法在光滑凸函数上比基于裁剪的算法具有更好的收敛性。我们证实了我们的理论与合成实验以及基准数据集上的实验。