模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2024, Vol. 37 Issue (9): 824-838    DOI: 10.16451/j.cnki.issn1003-6059.202409006
Researches and Applications Current Issue| Next Issue| Archive| Adv Search |
Secure and Efficient Federated Learning for Multi-domain Data Scenarios
JIN Chunhua1, LI Lulu1, WANG Jiahao1, JI Ling1, LIU Xinying1, CHEN Liqing1,2, ZHANG Hao1, WENG Jian3
1. Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223003;
2. Fujian Provincial Key Laboratory of Network Security and Cryp-tology, Fujian Normal University, Fuzhou 350007;
3. College of Information Science and Technology, Jinan University, Guangzhou 510632

Download: PDF (1532 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  To tackle the challenges of poor generalization, catastrophic forgetting and privacy attacks that federated learning faces in multi-domain data training, a scheme for secure and efficient federated learning for multi-domain scenarios(SEFL-MDS) is proposed. In the local training phase, knowledge distillation technology is employed to prevent catastrophic forgetting during multi-domain data training, while accelerating knowledge transfer across domains to improve training efficiency. In the uploading phase, Gaussian noise is added to locally updated gradients and generalization differences across domains using the Gaussian differential privacy mechanism to ensure secure data uploads and enhance the confidentiality of the training process. In the aggregation phase, a dynamic generalization-weighted algorithm is utilized to reduce generalization differences across domains, thereby enhancing the generalization capability. Theoretical analysis demonstrates the high robustness of the proposed scheme. Experiments on PACS and office-Home datasets show that the proposed scheme achieves higher accuracy with reduced training time.
Key wordsFederated Learning      Domain Generalization      Inference Attack      Knowledge Distillation      Differential Privacy     
Received: 31 July 2024     
ZTFLH: TP 309  
  TP 181  
Fund:Major Research Project of the Natural Science Foundation of the Jiangsu Higher Education Institutions(No.23KJA520003), Postgraduate Research & Practice Innovation Program of Jiangsu Province(No.SJCX24_2144), Postgraduate Scientific Innovation Plan Project of Huaiyin Institute of Techno-logy(No.HGYK202418)
Corresponding Authors: JIN Chunhua, Ph.D., associate professor. Her research in-terests include information security, cloud sto-rage, blockchain and federated learning.   
About author:: LI Lulu, Master student. His research interests include cryptography, blockchain and federated learning. WANG Jiahao, Master student. His research interests include cryptography, blockchain and federated learning. JI Ling, Master student. Her research interests include image encryption and image retrieval. LIU Xinying, Master student. Her research interests include cryptography and federated learning. CHEN Liqing, Ph.D., associate profe-ssor. His research interests include information and network security, and public key cryptography. ZHANG Hao, Ph.D., associate professor. His research interests include transportation big data, traffic safety, and logistics and su-pply chain. WENG Jian, Ph.D., professor. His research interests include public key cryptography, cloud security and blockchain.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
JIN Chunhua
LI Lulu
WANG Jiahao
JI Ling
LIU Xinying
CHEN Liqing
ZHANG Hao
WENG Jian
Cite this article:   
JIN Chunhua,LI Lulu,WANG Jiahao等. Secure and Efficient Federated Learning for Multi-domain Data Scenarios[J]. Pattern Recognition and Artificial Intelligence, 2024, 37(9): 824-838.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202409006      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2024/V37/I9/824
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn