关键词: 水电数据, 数据融合, 联邦学习, 推理攻击, 数据隐私

Abstract: To address the issues of cross-media data fusion modeling and privacy protection in the hydropower industry, a dual vertical federated learning framework incorporating secret sharing technology was proposed. First, the participant nodes were stratified, with lower-tier nodes responsible for preliminary modeling, intermediate-tier nodes overseeing pre-model aggregation and optimization, and central nodes generating the final model. Then, in order to strengthen data privacy protection and prevent inference attacks, an inter-mediate parameter protection mechanism based on secret sharing technology was introduced, the communication data between the data owner and the model trainer was fragmented and divided, which ensured the covertness of the correspondence between the model parameters and the trainer, thereby increasing the complexity of inference attacks. Finally, in order to optimize the model aggregation process of federated learning, a node evaluation mechanism based on the disparity in information quantities was introduced, in which the node dissimilarity and data volume were assessed. The weights of different nodes in model aggregation were finely adjusted, and the contribution of suspected malicious nodes was eliminated, thus optimizing the performance and convergence speed of the model. In the experimental part, the dataset was selected as the real data of Guodian Dadu River Basin Hydropower Development Co. The results show that: the intermediate parameter protection mechanism based on the secret sharing technology is more stable in the convergence process and the convergence speed is improved by 14.2% compared with the differential privacy protection mechanism.Upon the integration of node evaluation mechanism based on information disparity, the model's error is reduced by 3.7% and convergence speed is boosted by 13.4% compared with Federated Averaging Algorithm. It is verified that the proposed solution has addressed the issue of cross-media data fusion modeling for hydropower data, and it possesses the advantages of data privacy protection and model convergence acceleration.

Key words: hydropower data, data fusion, federated learning, inference attacks, data privacy