VeriFU:可验证的联邦遗忘学习OA

Federated unlearning enables clients to withdraw their contributions from a global model.However,en-abling clients to verify whether the server has honestly and effectively removed their contributions remains a criti-cal challenge.To address this aspect,which has been largely overlooked in existing literature,a verification model based on zero-knowledge proofs was constructed,and a comprehensive framework for verifiable federated unlearn-ing was proposed.Combined with a dynamically updated Merkle tree structure,a novel verifiable federated un-learning scheme was presented characterized by its zero-knowledge property.This allows for the efficient genera-tion of cryptographic proofs for server unlearning operations while rigorously protecting the data privacy of other clients.We evaluate the effectiveness and computational overhead of the proposed scheme.Comparative experi-ments with Rivest-Shamir-Adleman(RSA)accumulator-based and Hash chain-based schemes demonstrate that,when the model parameter size reaches the order of 105,the proposed scheme improves proof generation speed by approximately two orders of magnitude and verification speed by 13.2 times compared to the RSA-based scheme.Furthermore,it effectively avoids the scalability bottleneck of data linear growth in verification overhead inherent in Hash chain-based schemes.