Trust and Resilience in Federated Learning Through Smart Contracts Enabled Decentralized Systems
This addresses trust problems in federated learning for applications requiring secure data collaboration, though it appears incremental.
The paper tackles trust and reliability issues in federated learning by implementing a decentralized system using IPFS and smart contracts to manage parameter updates securely. Experimental results with two aggregation methods (averaging and federated proximal) confirm the system's feasibility.
In this paper, we present a study of a Federated Learning (FL) system, based on the use of decentralized architectures to ensure trust and increase reliability. The system is based on the idea that the FL collaborators upload the (ciphered) model parameters on the Inter-Planetary File System (IPFS) and interact with a dedicated smart contract to track their behavior. Thank to this smart contract, the phases of parameter updates are managed efficiently, thereby strengthening data security. We have carried out an experimental study that exploits two different methods of weight aggregation, i.e., a classic averaging scheme and a federated proximal aggregation. The results confirm the feasibility of the proposal.