Е-Публикации
Технически университет - София

Abstract: In recent years, rapid technological advancements have propelled blockchain and artificial intelligence (AI) into prominent roles within the digital industry, each having unique applications. Blockchain, recognized for its secure and transparent data storage, and AI, a powerful tool for data analysis and decision making, exhibit common features that render them complementary. At the same time, machine learning has become a robust and influential technology, adopted by many companies to address non-trivial technical problems. This adoption is fueled by the vast amounts of data generated and utilized in daily operations. An intriguing intersection of blockchain and AI occurs in the realm of federated learning, a distributed approach allowing multiple parties to collaboratively train a shared model without centralizing data. This paper presents a decentralized platform FBLearn for the implementation of federated learning in blockchain, which enables us to harness the benefits of federated learning without the necessity of exchanging sensitive customer or product data, thereby fostering trustless collaboration. As the decentralized blockchain network is introduced in the distributed model training to replace the centralized server, global model aggregation approaches have to be utilized. This paper investigates several techniques for model aggregation based on the local model average and ensemble using either local or globally distributed validation data for model evaluation. The suggested aggregation approaches are experimentally evaluated based on two use cases of the FBLearn platform: credit risk scoring using a random forest classifier and credit card fraud detection using a logistic regression. The experimental results confirm that the suggested adaptive weight calculation and ensemble techniques based on the quality of local training data enhance the robustness of the global model. The performance evaluation metrics and ROC curves prove that the aggregation strategies successfully isolate the influence of the low-quality models on the final model. The proposed system’s ability to outperform models created with separate datasets underscores its potential to enhance collaborative efforts and to improve the accuracy of the final global model compared to each of the local models. Integrating blockchain and federated learning presents a forward-looking approach to data collaboration while addressing privacy concerns.

References

1. Haber S. Stornetta W. S. How to time-stamp a digital document Advances in Cryptology-CRYPTO’90 Menezes A.J. Vanstone S.A. Lecture Notes in Computer Science Springer Berlin/Heidelberg, Germany 1990 537 437 455
2. Nakamoto S. Bitcoin: A Peer-to-Peer Electronic Cash System, Technical Report 2008 Available online: http://bitcoin.org/bitcoin.pdf (accessed on 4 September 2024)
3. Peng C. Akca S. Rajan A. SIF: A Framework for Solidity Contract Instrumentation and Analysis. Technical Report, University of Edinburgh, UK, May 2019 Available online: https://arxiv.org/abs/1905.01659 (accessed on 4 September 2024)
4. Rudman R. Bruwer R. Defining Web 3.0: Opportunities and challenges Electron. Libr. 2016 34 132 154 10.1108/EL-08-2014-0140
5. Alabdulwahhab F.A. Web 3.0: The decentralized web blockchain networks and protocol innovation Proceedings of the 2018 1st International Conference on Computer Applications & Information Security (ICCAIS) Riyadh, Saudi Arabia 4–6 April 2018 1 4
6. Rumelhart D.E. McClelland J.L. Parallel Distributed Processing: Explorations in the Microstructure of Cognition MIT Press Cambridge, MA, USA 1987
7. Fischer L. Ehrlinger L. Geist V. Ramler R. Sobieczky F. Zellinger W. Moser B. Applying AI in practice: Key challenges and lessons learned Machine Learning and Knowledge Extraction Holzinger A. Kieseberg P. Tjoa A. Weippl E. Lecture Notes in Computer Science Springer Cham, Switzerland 2020 Volume 12279 451 471
8. Shi S. Tse R. Luo W. D’Addona S. Pau G. Machine learning-driven credit risk: A systemic review Neural Comput. Appl. 2022 34 14327 14339 10.1007/s00521-022-07472-2
9. Li T. Sahu A.K. Talwalkar A. Smith V. Federated learning: Challenges, methods, and future directions IEEE Signal Process. Mag. 2020 37 50 60 10.1109/MSP.2020.2975749
10. McMahan B. Moore E. Ramage D. Hampson S. Arcas B.A. Communication-efficient learning of deep networks from decentralized data Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR Fort Lauderdale, FL, USA 20–22 April 2017 1273 1282
11. Gosselin R. Vieu L. Loukil F. Benoit A. Privacy and Security in Federated Learning: A Survey Appl. Sci. 2022 12 9901 10.3390/app12199901
12. Sun N. Wang W. Tong Y. Liu K. Blockchain based federated learning for intrusion detection for Internet of Things Front. Comput. Sci. 2023 18 185328 10.1007/s11704-023-3026-8
13. Li Q. Wang W. Zhu Y. Ying Z. BOppCL: Blockchain-enabled opportunistic federated learning applied in intelligent transportation systems Electronics 2024 13 136 10.3390/electronics13010136
14. Wang L. Guan C. Improving security in the internet of vehicles: A blockchain-based data sharing scheme Electronics 2024 13 714 10.3390/electronics13040714
15. Zhu C. Zhu X. Qin T. An efficient privacy protection mechanism for blockchain-based federated learning system in UAV-MEC Networks Sensors 2024 24 1364 10.3390/s24051364
16. Javed A.R. Hassan M.A. Shahzad F. Ahmed W. Singh S. Baker T. Gadekallu T.R. Integration of blockchain technology and federated learning in vehicular (IoT) networks: A comprehensive survey Sensors 2022 22 4394 10.3390/s22124394
17. Hai T. Zhou J. Srividhya S.R. Jain S.K. Young P. Agrawal S. BVFLEMR: An integrated federated learning and blockchain technology for cloud-based medical records recommendation system J. Cloud Comput. 2022 11 22
18. Ashraf E. Areed N.F.F. Salem H. Abdelhay E.H. Farouk A. FIDChain: Federated intrusion detection system for blockchain-enabled iot healthcare applications Healthcare 2022 10 1110 10.3390/healthcare10061110 35742161
19. Bi L. Muazu T. Samuel O. IoT: A decentralized trust management system using blockchain-empowered federated learning Sustainability 2023 15 374 10.3390/su15010374
20. Li C. Yuan Y. Wang F.-Y. Blockchain-enabled federated learning: A survey Proceedings of the 2021 IEEE 1st International Conference on Digital Twins and Parallel Intelligence (DTPI) Beijing, China 15 July–15 August 2021 286 289
21. Wu L. Ruan W. Hu J. He Y. A survey on blockchain-based federated learning Future Internet 2023 15 400 10.3390/fi15120400
22. Wang Z. Yan B. Dong A. Blockchain Empowered Federated Learning for Data Sharing Incentive Mechanism Procedia Comput. Sci. 2022 202 348 353 10.1016/j.procs.2022.04.047
23. Xu Y. Lu Z. Gai K. Duan Q. Lin J. Wu J. Choo K.-K.R. BESIFL: Blockchain-empowered secure and incentive federated learning paradigm in IoT IEEE Internet Things 2021 10 6561 6573 10.1109/JIOT.2021.3138693
24. Tian Y. Guo Z. Zhang J. Al-Ars Z. 2023. DFL: High-performance blockchain-based federated learning Distrib. Ledger Technol. Res. Pract. 2023 2 1 25 10.1145/3600225
25. Yang J. Zhang W. Guo Z. Gao Z. TrustDFL: A blockchain-based verifiable and trusty decentralized federated learning framework Electronics 2024 13 86 10.3390/electronics13010086
26. Ouyang K. Yu J. Cao X. Liao Z. Towards reliable federated learning using blockchain-based reverse auctions and reputation incentives Symmetry 2023 15 2179 10.3390/sym15122179
27. Wu C. Wu F. Lyu L. Huang Y. Xie X. Communication-efficient federated learning via knowledge distillation Nat. Commun. 2022 13 2032 10.1038/s41467-022-29763-x
28. Kim G. Kim Y. The threat of disruptive jamming to blockchain-based decentralized federated learning in wireless networks Sensors 2024 24 535 10.3390/s24020535
29. Wan C. Wang Y. Xu J. Wu J. Zhang T. Wang Y. Research on privacy protection in federated learning combining distillation defense and blockchain Electronics 2024 13 679 10.3390/electronics13040679
30. Begum K. Mozumder M.A.I. Joo M.-I. Kim H.-C. BFLIDS: Blockchain-driven federated learning for intrusion detection in IoMT networks Sensors 2024 24 4591 10.3390/s24144591 39065989
31. Zhang H. Zhang P. Hu M. Liu M. Wang J. FedUB: Federated learning algorithm based on update bias Mathematics 2024 12 1601 10.3390/math12101601
32. Marin Machado de Souza R. Holm A. Biczyk M. de Castro L.N. A systematic literature review on the use of federated learning and bioinspired computing Electronics 2024 13 3157 10.3390/electronics13163157
33. Shang C. Gu F. Jiang J. Evolutionary multi-model federated learning on malicious and heterogeneous data Proceedings of the 2023 IEEE International Conference on Data Mining Workshops (ICDMW) Shanghai, China 1–4 December 2023 386 395
34. Ahmed A. Alabi O. Secure and scalable blockchain-based federated learning for cryptocurrency fraud detection: A systematic review IEEE Access 2024 12 102219 102241 10.1109/ACCESS.2024.3429205
35. Baabdullah T. Alzahrani A. Rawat D.B. Liu C. Efficiency of federated learning and blockchain in preserving privacy and enhancing the performance of credit card fraud detection (CCFD) systems Future Internet 2024 16 196 10.3390/fi16060196
36. Liu B. Tang Q. Secure data sharing in federated learning through blockchain-based aggregation Future Internet 2024 16 133 10.3390/fi16040133
37. Wang H. Gao H. Ma T. Li C. Jing T. A hierarchical blockchain-enabled distributed federated learning system with model-contribution based rewarding Digit. Commun. Netw. 2024 in press 10.1016/j.dcan.2024.07.002
38. Djolev D. Lazarova M. Nakov O. Blockchain based trusted distributed machine learning for credit scoring Proceedings of the 2023 International Scientific Conference on Computer Science (COMSCI) Sozopol, Bulgaria 18–20 September 2023
39. Djolev D. Lazarova M. Nakov O. Federated learning for credit scoring model using blockchain Communications in Computer and Information Science: Optimization, Learning Algorithms and Applications Pereira A. Mendes A. Fernandes F. Pacheco M. Coelho J. Lima J. Springer Cham, Switzerland 2024 Volume 1981
40. FELT—Federating Learning Token Available online: https://github.com/FELT-Labs/federated-learning-token (accessed on 4 September 2024)
41. Gencturk M. Sinaci A. Cicekli N. BOFRF: A novel boosting-based federated random forest algorithm on horizontally partitioned data IEEE Access 2022 10 89835 89851 10.1109/ACCESS.2022.3202008
42. Matthews B. Comparison of the predicted and observed secondary structure of T4 phage lysozyme Biochim. Et Biophys. Acta (BBA)—Protein Struct. 1975 405 442 451 10.1016/0005-2795(75)90109-9
43. Home Credit Default Risk Available online: https://www.kaggle.com/competitions/home-credit-default-risk (accessed on 4 September 2024)
44. Credit Card Fraud Detection Dataset 2023 Available online: https://www.kaggle.com/datasets/nelgiriyewithana/credit-card-fraud-detection-dataset-2023/data (accessed on 4 September 2024)
45. Data Preprocessing for Credit Score Classification Available online: https://www.kaggle.com/code/bugaiovaolena/data-preprocessing-for-credit-score-classification (accessed on 4 September 2024)

Issue