Trusted Data Sharing Mechanism Based on Blockchain and Federated Learning in Space-Air-Ground Integrated Networks

Abstract

Network data is distributed data on electricity, with the explosive growth of network data, and it has become an inevitable trend of network development to synergized and shared crossdomain scattered data and enhances the value transmission of network data. Federated learning, as a technology that combines data value delivery and data privacy security, is widely concerned in the process of data sharing. However, currently federated learning is used within a single business system. In the process of crossdomain data sharing, how to ensure the data trust, model trust, and result trust of federated learning is still an urgent problem to be solved. To this end, we designed to use blockchain structure to record each behavior of data sharing. Based on its tamper-proof and traceability, combined with cryptography technology, we constructed an endogenous trusted architecture for crossdomain data sharing. In addition, a reverse auction node incentive mechanism based on high credit preference is designed to solve the common problems in data sharing, such as low enthusiasm of users in sharing, unstable data quality of contributions, and unreasonable distribution of data sharing benefits. Through theoretical analysis and experimental verification, it can be seen that the incentive mechanism designed in this paper can meet the authenticity, user rationality, and budget feasibility. On this basis, it can motivate users to participate in data sharing, improve the average quality of data shared by users, and ensure security and trustworthiness and resist malicious attacks to a certain extent.