We propose a novel privacy-preserving uplink over-the-air computation (AirComp) method, termed FLORAS, for single-input single-output (SISO) wireless federated learning (FL) systems. From the communication design perspective, FLORAS eliminates the requirement of channel state information at the transmitters (CSIT) by leveraging the properties of orthogonal sequences. From the privacy perspective, we prove that FLORAS can offer both item-level and client-level differential privacy (DP) guarantees. Moreover, by adjusting the system parameters, FLORAS can flexibly achieve different DP levels at no additional cost. A novel FL convergence bound is derived which, combined with the privacy guarantees, allows for a smooth tradeoff between convergence rate and differential privacy levels. Numerical results demonstrate the advantages of FLORAS compared with the baseline AirComp method, and validate that our analytical results can guide the design of privacy-preserving FL with different tradeoff requirements on the model convergence and privacy levels.

翻译：我们提出了一种新颖的隐私保护上行链路空中计算（AirComp）方法，命名为FLORAS，适用于单输入单输出（SISO）无线联邦学习（FL）系统。从通信设计角度看，FLORAS利用正交序列的特性，消除了发射机侧信道状态信息（CSIT）的需求。从隐私角度看，我们证明FLORAS能够同时提供条目级和客户端级差分隐私（DP）保障。此外，通过调整系统参数，FLORAS可以在不增加额外成本的情况下灵活实现不同的DP级别。我们推导出了一个新颖的FL收敛界，该界与隐私保障相结合，实现了收敛速率与差分隐私级别之间的平滑权衡。数值结果证明了FLORAS相较于基线AirComp方法的优势，并验证了我们的分析结果能够指导具有不同模型收敛与隐私水平权衡需求的隐私保护FL设计。