网络与信息安全学报2025，Vol.11Issue(5)：88-100,13.DOI:10.11959/j.issn.2096-109x.2025056
基于风险权值聚合联邦学习的金融欺诈检测模型
Financial fraud detection model based on risk weight aggregation federated learning
摘要
Abstract
Financial fraud had caused significant losses to financial institutions and consumers,making the rapid,effective,and accurate identification and prevention of financial fraud a widely concerned issue.Machine learning and deep learning technologies had received extensive research attention due to their capability to effectively detect dynamic and changing fraud patterns.However,the privacy and confidentiality requirements of financial data were found to limit the practical application of data-driven intelligent analysis technologies,including deep learning,in the financial field.Therefore,research on how to conduct collaborative training and establish effective fraud detec-tion models while ensuring data privacy and security was considered to be of great value.To address these chal-lenges,a risk weight aggregation federated learning(FedRWA)method was proposed for multi-model fusion.A central anomaly detection model was constructed to achieve multi-source sensitive data model fusion learning while ensuring data privacy.This approach enabled the central joint model to accurately capture the fraud risk char-acteristics of each institution's private dataset,thereby improving fraud detection effectiveness.To verify the effec-tiveness of the proposed method,experiments were conducted using a credit card transaction dataset.The experi-mental results demonstrate that the FedRWA method performs better than numerous cutting-edge federated learning methods,could detect more and larger fraud samples,and further enhances the security of private data.关键词
联邦学习/金融欺诈/风险权值/欺诈检测Key words
federated learning/financial fraud/risk weight/fraud detection分类
信息技术与安全科学引用本文复制引用
孙元林,王楠,张焘,刘娟,赵沁馨..基于风险权值聚合联邦学习的金融欺诈检测模型[J].网络与信息安全学报,2025,11(5):88-100,13.基金项目
国家自然科学基金(62202042) （62202042）
中央高校基本科研业务费专项基金(2024JBMC031) （2024JBMC031）
航空科学基金(ASFC-2024Z0710M5002) （ASFC-2024Z0710M5002）
先进密码技术与系统安全四川省重点实验室开放课题资助项目(SKLACSS-202312) The Natural Science Foundation of China(62202042),Fundamental Research Funds for the Central Univer-sities(2024JBMC031),Aeronautical Science Foundation of China(ASFC-2024Z0710M5002),OpenFund of Advanced Cryp-tography and System Security Key Laboratory of Sichuan Province(SKLACSS-202312) （SKLACSS-202312）
