Federated learning is predicated on the provision of high-quality data by multiple clients, which is then used to train global models. A plethora of incentive mechanism studies have been conducted with the objective of promoting the provision of high-quality data by clients. These studies have focused on the distribution of benefits to clients. However, the incentives of federated learning are transactional in nature, and the issue of atomicity of transactions has not been addressed. Furthermore, the data quality of individual clients participating in training varies, and they may participate negatively in training out of privacy leakage concerns.

Consequently, we propose the inaugural atomistic incentive scheme with privacy preservation in the FL setting: $\pi \text{FL}$ ($\textbf{p}$rivacy, $\textbf{a}$tomic, $\textbf{i}$ncentive). This scheme establishes a more dependable training environment based on Shapley valuation, secure multiparty computation, and smart contracts. Consequently, it ensures that each client’s contribution can be accurately measured and appropriately rewarded, improves the accuracy and efficiency of model training, and enhances the sustainability and reliability of the FL system. The efficacy of this mechanism is demonstrated through comprehensive experimental analysis. It is evident that this mechanism not only protects the privacy of trainers and provides atomic training rewards but also improves the model performance of federated learning, with an accuracy improvement of at least 8%.