Enhancing Federated Learning Security, Scalability, and Future Incentives

Abstract

This study delves into the integration of Storj and blockchain technology within the context of federated learning (FL) and its implications for scalability and efficiency. By leveraging blockchain, we aimed to bolster security and transparency, while also addressing storage challenges through the integration of Incremental Learning. Our findings revealed that while the utilization of Storj led to marginally higher federated server storage requirements compared to local storage, particularly as the number of clients increased, there was also a slight increase in the time required for the federated learning process when Storj was integrated, especially with a larger number of clients.