网络与信息安全学报2026，Vol.12Issue(2)：104-117,14.DOI:10.11959/j.issn.2096-109x.AQ26024
VeriFU:可验证的联邦遗忘学习
VeriFU:verifiable federated unlearning
摘要
Abstract
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.关键词
联邦遗忘学习/零知识证明/默克尔树/遗忘验证Key words
federated unlearning/zero-knowledge proof/Merkle tree/unlearning verification分类
信息技术与安全科学引用本文复制引用
江泽豪,熊金波,黄佳毅,张媛媛,田有亮..VeriFU:可验证的联邦遗忘学习[J].网络与信息安全学报,2026,12(2):104-117,14.基金项目
国家自然科学基金资助项目(No.62272102,No.62272123) （No.62272102,No.62272123）
福建省自然科学基金资助项目(No.2023J02014,No.2024J08163) The National Natural Science Foundation of China(No.62272102,No.62272123),The Natural Science Foundation Project of Fujian Province(No.2023J02014,No.2024J08163) （No.2023J02014,No.2024J08163）
