Decentralized Federated Unlearning on Blockchain

arXiv:2402.16294v1 Announce Type: new
Abstract: Blockchained Federated Learning (FL) has been gaining traction for ensuring the integrity and traceability of FL processes. Blockchained FL involves participants training models locally with their data and subsequently publishing the models on the blockchain, forming a Directed Acyclic Graph (DAG)-like inheritance structure that represents the model relationship. However, this particular DAG-based structure presents challenges in updating models with sensitive data, due to the complexity and overhead involved. To address this, we propose Blockchained Federated …

arxiv blockchain cs.ai cs.cr data decentralized federated federated learning forming graph integrity locally processes publishing relationship structure traceability training