Trustworthy Federated Learning (TFL) typically leverages protection mechanisms to guarantee privacy. However, protection mechanisms inevitably introduce utility loss or efficiency reduction while protecting data privacy. Therefore, protection mechanisms and their parameters should be carefully chosen to strike an optimal tradeoff between \textit{privacy leakage}, \textit{utility loss}, and \textit{efficiency reduction}. To this end, federated learning practitioners need tools to measure the three factors and optimize the tradeoff between them to choose the protection mechanism that is most appropriate to the application at hand. Motivated by this requirement, we propose a framework that (1) formulates TFL as a problem of finding a protection mechanism to optimize the tradeoff between privacy leakage, utility loss, and efficiency reduction and (2) formally defines bounded measurements of the three factors. We then propose a meta-learning algorithm to approximate this optimization problem and find optimal protection parameters for representative protection mechanisms, including Randomization, Homomorphic Encryption, Secret Sharing, and Compression. We further design estimation algorithms to quantify these found optimal protection parameters in a practical horizontal federated learning setting and provide a theoretical analysis of the estimation error.

翻译：可信联邦学习（TFL）通常借助保护机制来保障隐私安全。然而，保护机制在保护数据隐私的同时，不可避免地会引入效用损失或效率下降。因此，需要精心选择保护机制及其参数，以在\textit{隐私泄露}、\textit{效用损失}和\textit{效率下降}三者之间取得最优权衡。为此，联邦学习从业者需要能够量化这三个因素并优化其权衡关系的工具，以便针对当前应用选择最合适的保护机制。基于这一需求，我们提出一个框架，该框架：(1) 将TFL形式化为寻找最优保护机制以优化隐私泄露、效用损失和效率下降之间权衡的问题；(2) 正式定义了这三个因素的有界度量方法。随后，我们提出一种元学习算法来近似求解这一优化问题，并为包括随机化、同态加密、秘密共享和压缩在内的典型保护机制寻找最优保护参数。我们进一步设计了估计算法，以在实际横向联邦学习场景中量化这些最优保护参数，并给出了估计误差的理论分析。