Federated learning-driven dual blockchain for data sharing and reputation management in Internet of medical things

被引:1
作者
Gan, Chenquan [1 ,2 ]
Xiao, Xinghai [2 ]
Zhu, Qingyi [1 ]
Jain, Deepak Kumar [3 ,4 ]
Saini, Akanksha [5 ]
Hussain, Amir [6 ]
机构
[1] Chongqing Univ Posts & Telecommun, Sch Cyber Secur & Informat Law, Chongqing, Peoples R China
[2] Chongqing Univ Posts & Telecommun, Sch Commun & Informat Engn, Chongqing, Peoples R China
[3] Dalian Univ Technol, Key Lab Intelligent Control & Optimizat Ind Equipm, Minist Educ, Dalian 116024, Peoples R China
[4] Symbiosis Int Univ, Symbiosis Inst Technol, Pune, India
[5] RMIT Univ, Coll Business & Law, Melbourne, Australia
[6] Edinburgh Napier Univ, Ctr AI & Robot, Edinburgh, Scotland
基金
英国工程与自然科学研究理事会;
关键词
internet of medical things; data sharing; reputation management; federated learning; model-quality blockchain; reputation-incentive blockchain;
D O I
10.1111/exsy.13714
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the Internet of Medical Things (IoMT), the vulnerability of federated learning (FL) to single points of failure, low-quality nodes, and poisoning attacks necessitates innovative solutions. This article introduces a FL-driven dual-blockchain approach to address these challenges and improve data sharing and reputation management. Our approach comprises two blockchains: the Model Quality Blockchain (MQchain) and the Reputation Incentive Blockchain (RIchain). MQchain utilizes an enhanced Proof of Quality (PoQ) consensus algorithm to exclude low-quality nodes from participating in aggregation, effectively mitigating single points of failure and poisoning attacks by leveraging node reputation and quality thresholds. In parallel, RIchain incorporates a reputation evaluation, incentive mechanism, and index query mechanism, allowing for rapid and comprehensive node evaluation, thus identifying high-reputation nodes for MQchain. Security analysis confirms the theoretical soundness of the proposed method. Experimental evaluation using real medical datasets, specifically MedMNIST, demonstrates the remarkable resilience of our approach against attacks compared to three alternative methods.
引用
收藏
页数:23
相关论文
共 37 条
[1]   Hyperledger Fabric: A Distributed Operating System for Permissioned Blockchains [J].
Androulaki, Elli ;
Barger, Artem ;
Bortnikov, Vita ;
Cachin, Christian ;
Christidis, Konstantinos ;
De Caro, Angelo ;
Enyeart, David ;
Ferris, Christopher ;
Laventman, Gennady ;
Manevich, Yacov ;
Muralidharan, Srinivasan ;
Murthy, Chet ;
Binh Nguyen ;
Sethi, Manish ;
Singh, Gari ;
Smith, Keith ;
Sorniotti, Alessandro ;
Stathakopoulou, Chrysoula ;
Vukolic, Marko ;
Cocco, Sharon Weed ;
Yellick, Jason .
EUROSYS '18: PROCEEDINGS OF THE THIRTEENTH EUROSYS CONFERENCE, 2018,
[2]   Personalized Real-Time Federated Learning for Epileptic Seizure Detection [J].
Baghersalimi, Saleh ;
Teijeiro, Tomas ;
Atienza, David ;
Aminifar, Amir .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (02) :898-909
[3]   Towards a Secure and Sustainable Internet of Medical Things (IoMT): Requirements, Design Challenges, Security Techniques, and Future Trends [J].
Bhushan, Bharat ;
Kumar, Avinash ;
Agarwal, Ambuj Kumar ;
Kumar, Amit ;
Bhattacharya, Pronaya ;
Kumar, Arun .
SUSTAINABILITY, 2023, 15 (07)
[4]   A blockchain-based preserving and sharing system for medical data privacy [J].
Chen, Zeng ;
Xu, Weidong ;
Wang, Bingtao ;
Yu, Hua .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2021, 124 :338-350
[5]   Federated Learning for Smart Healthcare: A Survey [J].
Dinh C Nguyen ;
Quoc-Viet Pham ;
Pathirana, Pubudu N. ;
Ding, Ming ;
Seneviratne, Aruna ;
Lin, Zihuai ;
Dobre, Octavia ;
Hwang, Won-Joo .
ACM COMPUTING SURVEYS, 2023, 55 (03)
[6]   When Collaborative Federated Learning Meets Blockchain to Preserve Privacy in Healthcare [J].
El Houda, Zakaria Abou ;
Hafid, Abdelhakim Senhaji ;
Khoukhi, Lyes ;
Brik, Bouziane .
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2023, 10 (05) :2455-2465
[7]   BFCRI: A Blockchain-Based Framework for Crowdsourcing With Reputation and Incentive [J].
Fu, Shaojing ;
Huang, XueLun ;
Liu, Lin ;
Luo, Yuchuan .
IEEE TRANSACTIONS ON CLOUD COMPUTING, 2023, 11 (02) :2158-2174
[8]   A security model to protect the isolation of medical data in the cloud using hybrid cryptography [J].
Gadde, Swetha ;
Amutharaj, J. ;
Usha, S. .
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS, 2023, 73
[9]   An encrypted medical blockchain data search method with access control mechanism [J].
Gan, Chenquan ;
Yang, Hongpeng ;
Zhu, Qingyi ;
Zhang, Yiye ;
Saini, Akanksha .
INFORMATION PROCESSING & MANAGEMENT, 2023, 60 (06)
[10]  
Haghighi S., 2018, J OPEN SOURCE SOFTW, V3, P729, DOI [10.21105/joss.00729, DOI 10.21105/JOSS.00729]