计算机与现代化Issue(8)：63-69,88,8.DOI:10.3969/j.issn.1006-2475.2025.08.009
基于联邦学习的数据隐私保护方案
A Data Privacy Protection Scheme Based on Federated Learning
摘要
Abstract
The current healthcare data domain faces the issue of data silos,which restricts the flow and sharing of data among dif-ferent institutions and hinders cross-institutional treatment for patients.To address this problem,this paper proposes a privacy protection scheme based on federated learning(Federated Learning with Schnorr Zero-knowledge Based Identity Authentication and Differential Privacy Protection,FL-SZIDP).Firstly,a data-sharing framework based on federated learning is established.Secondly,to defend against adversaries attempting to steal original data through reverse attacks,differential privacy noise is added to the model parameters uploaded by each participant.To prevent malicious participants from joining the federated learn-ing process,identity authentication based on Schnorr zero-knowledge proof is performed,ensuring the credibility of the partici-pants'identities.Finally,the effectiveness of the proposed algorithm is verified using the MNIST data set.The experimental re-sults show that the scheme FL-SZIDP ensures accuracy while protecting privacy.关键词
联邦学习/隐私保护/差分隐私/数据安全Key words
federal learning/privacy protection/differential privacy/data security分类
信息技术与安全科学引用本文复制引用
程钰雯,景义君,时自成,荆长强,郭锋,武传坤..基于联邦学习的数据隐私保护方案[J].计算机与现代化,2025,(8):63-69,88,8.基金项目
国家自然科学基金青年基金资助项目(61901206) （61901206）
