Data Privacy Protection Sharing Strategy Based on Consortium Blockchain and Federated Learning
Xiaoqing Feng, Lei Chen · 2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT) · 2022
The blockchain is non-tamperable and has a strong certificate storage function, it can realize controllable traceability of data. Federated learning can realize the availability and invisibility of data. Therefore, they have a certain complementarity in function. If they can be combined with each other, it can not only effectively improve the efficiency of data sharing, but also protect data privacy. This paper studies the privacy protection strategy of enterprise information data based on consortium blockchain and federated learning. Starting from the actual needs of data sharing in the big data analysis scenario, using consortium blockchain to build a decentralized trusted network, combined with The federated learning framework realizes the joint sharing modeling of multiparty data. A RAFT efficient consensus mechanism based on credibility guarantees the traceability of the federated learning process is studied, and finally realizes a private and secure enterprise credit information data sharing system.