Participant Selection for Efficient and Trusted Federated Learning in Blockchain-Assisted Hierarchical Federated Learning Architectures

Future Internet, Journal Year: 2025, Volume and Issue: 17(2), P. 75 - 75

Published: Feb. 8, 2025

Federated learning has attracted widespread attention due to its strong capabilities of privacy protection, making it a powerful supporting technology for addressing data silos in the future. However, federated still lags significantly behind traditional centralized terms efficiency and system security. In this paper, we first construct hierarchical architecture integrated with blockchain based on cooperation cloud, edge, terminal, which ability enhance security while reducing introduction costs blockchain. Under architecture, propose semi-asynchronous aggregation scheme at edge layer introduce that combines synchronous cloud end improve efficiency. Furthermore, present multi-objective node selection considers various influencing factors such as We formulate problem Markov Decision Process (MDP) solution deep reinforcement address more efficiently. The experimental results show proposed can effectively addition, DQN-based algorithm efficiently realize optimal policy.

Language: Английский

Pivacy-preserving federated learning based on multi-key fully homomorphic encryption and trusted execution environment

Peer-to-Peer Networking and Applications, Journal Year: 2025, Volume and Issue: 18(4)

Published: May 9, 2025

Language: Английский