BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model (2310.13403v1)
Abstract: With the increasing importance of machine learning, the privacy and security of training data have become critical. Federated learning, which stores data in distributed nodes and shares only model parameters, has gained significant attention for addressing this concern. However, a challenge arises in federated learning due to the Byzantine Attack Problem, where malicious local models can compromise the global model's performance during aggregation. This article proposes the Blockchain-based Byzantine-Robust Federated Learning (BRLF) model that combines federated learning with blockchain technology. This integration enables traceability of malicious models and provides incentives for locally trained clients. Our approach involves selecting the aggregation node based on Pearson's correlation coefficient, and we perform spectral clustering and calculate the average gradient within each cluster, validating its accuracy using local dataset of the aggregation nodes. Experimental results on public datasets demonstrate the superior byzantine robustness of our secure aggregation algorithm compared to other baseline byzantine robust aggregation methods, and proved our proposed model effectiveness in addressing the resource consumption problem.
- H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in International Conference on Artificial Intelligence and Statistics, 2016. [Online]. Available: https://api.semanticscholar.org/CorpusID:14955348
- T. Li, A. K. Sahu, A. Talwalkar, and V. Smith, “Federated learning: Challenges, methods, and future directions,” IEEE Signal Processing Magazine, vol. 37, pp. 50–60, 2019. [Online]. Available: https://api.semanticscholar.org/CorpusID:201126242
- Y. Qu, M. P. Uddin, C. Gan, Y. Xiang, L. Gao, and J. Yearwood, “Blockchain-enabled federated learning: A survey,” ACM Computing Surveys, vol. 55, pp. 1 – 35, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:237599179
- Y. Chen, L. Su, and J. Xu, “Distributed statistical machine learning in adversarial settings: Byzantine gradient descent,” in PERV, 2017. [Online]. Available: https://api.semanticscholar.org/CorpusID:58534983
- D. Cao, S. Chang, Z. Lin, G. Liu, and D. Sun, “Understanding distributed poisoning attack in federated learning,” 2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS), pp. 233–239, 2019. [Online]. Available: https://api.semanticscholar.org/CorpusID:210992177
- Y. Khazbak, T. Tan, and G. Cao, “Mlguard: Mitigating poisoning attacks in privacy preserving distributed collaborative learning,” 2020 29th International Conference on Computer Communications and Networks (ICCCN), pp. 1–9, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:218594342
- C. Fung, C. J. M. Yoon, and I. Beschastnikh, “The limitations of federated learning in sybil settings,” in International Symposium on Recent Advances in Intrusion Detection, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:221542915
- Y. Wang, T. Zhu, W. Chang, S. Shen, and W. Ren, “Model poisoning defense on federated learning: A validation based approach,” in International Conference on Network and System Security, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:230716867
- J. Tan, Y.-C. Liang, N. C. Luong, and D. T. Niyato, “Toward smart security enhancement of federated learning networks,” IEEE Network, vol. 35, pp. 340–347, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:221173074
- Z. Chen, P. Tian, W. Liao, and W. Yu, “Zero knowledge clustering based adversarial mitigation in heterogeneous federated learning,” IEEE Transactions on Network Science and Engineering, vol. 8, pp. 1070–1083, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:226622886
- X. Bao, C. Su, Y. Xiong, W. Huang, and Y. Hu, “Flchain: A blockchain for auditable federated learning with trust and incentive,” 2019 5th International Conference on Big Data Computing and Communications (BIGCOM), pp. 151–159, 2019. [Online]. Available: https://api.semanticscholar.org/CorpusID:208211278
- Z. Lin, Z. Wu, J. Zhu, and J. Huang, “A blockchain-based decentralized federated learning framework with dual-committees consensus,” Proceedings of the 2022 5th International Conference on Algorithms, Computing and Artificial Intelligence, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:257508657
- A. Islam and S. Y. K. Shin, “A blockchain-based privacy sensitive data acquisition scheme during pandemic through the facilitation of federated learning,” 2022 13th International Conference on Information and Communication Technology Convergence (ICTC), pp. 83–87, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:253880939
- Y. He, K. Huang, G. Zhang, F. R. Yu, J. Chen, and J. Li, “Bift: A blockchain-based federated learning system for connected and autonomous vehicles,” IEEE Internet of Things Journal, vol. 9, pp. 12 311–12 322, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:245154138
- M. Shayan, C. Fung, C. J. M. Yoon, and I. Beschastnikh, “Biscotti: A blockchain system for private and secure federated learning,” IEEE Transactions on Parallel and Distributed Systems, vol. 32, pp. 1513–1525, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:232042257
- H. Liu, S. Zhang, P. Zhang, X. Zhou, X. Shao, G. Pu, and Y. Zhang, “Blockchain and federated learning for collaborative intrusion detection in vehicular edge computing,” IEEE Transactions on Vehicular Technology, vol. 70, pp. 6073–6084, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:235589750
- H. Chen, S. A. Asif, J. Park, C.-C. Shen, and M. Bennis, “Robust blockchained federated learning with model validation and proof-of-stake inspired consensus,” ArXiv, vol. abs/2101.03300, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:231573565
- K. Yuan, Z. Wu, and Q. Ling, “A byzantine-resilient dual subgradient method for vertical federated learning,” ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4273–4277, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:249436560
- J.-H. Chen, M.-R. Chen, G. Zeng, and J. Weng, “Bdfl: A byzantine-fault-tolerance decentralized federated learning method for autonomous vehicle,” IEEE Transactions on Vehicular Technology, vol. 70, pp. 8639–8652, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:237598030
- W. Bao and J. He, “Boba: Byzantine-robust federated learning with label skewness,” ArXiv, vol. abs/2208.12932, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:251903346
- C. Chen, L. Lyu, Y. Liu, F. Wu, C. Chen, and G. Chen, “Byzantine-resilient federated learning via gradient memorization,” 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:246973253
- R. Jin, J. Hu, G. Min, and H. Lin, “Byzantine-robust and efficient federated learning for the internet of things,” IEEE Internet of Things Magazine, vol. 5, pp. 114–118, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:248698720
- M. Li, D. Xiao, J. Liang, and H. Huang, “Communication-efficient and byzantine-robust differentially private federated learning,” IEEE Communications Letters, vol. 26, pp. 1725–1729, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:249351301
- S. Nakamoto, “Bitcoin: A peer-to-peer electronic cash system,” 2008. [Online]. Available: https://api.semanticscholar.org/CorpusID:236214795
- H. Xiong, M. Chen, C. Wu, Y. Zhao, and W. Yi, “Research on progress of blockchain consensus algorithm: A review on recent progress of blockchain consensus algorithms,” Future Internet, vol. 14, p. 47, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:246434512
- K. Farooq, H. J. Syed, S. O. Alqahtani, W. A. E. Nagmeldin, A. O. Ibrahim, and A. Gani, “Blockchain federated learning for in-home health monitoring,” Electronics, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:255245541
- S. Aich, N. K. Sinai, S. Kumar, M. Ali, Y. R. Choi, M.-I. Joo, and H.-C. Kim, “Protecting personal healthcare record using blockchain & federated learning technologies,” 2021 23rd International Conference on Advanced Communication Technology (ICACT), pp. 109–112, 2021. [Online]. Available: https://api.semanticscholar.org/CorpusID:232235893
- W. Jiao, H. Zhao, P. Feng, and Q. Chen, “A blockchain federated learning scheme based on personalized differential privacy and reputation mechanisms,” 2023 4th International Conference on Information Science, Parallel and Distributed Systems (ISPDS), pp. 630–635, 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:261563809
- K. Pearson, “Contributions to the mathematical theory of evolution,” Proceedings of the Royal Society of London, vol. 54, pp. 329 – 333. [Online]. Available: https://api.semanticscholar.org/CorpusID:121108273
- U. von Luxburg, “A tutorial on spectral clustering,” Statistics and Computing, vol. 17, pp. 395–416, 2007. [Online]. Available: https://api.semanticscholar.org/CorpusID:3264198
- L. Li, W. Xu, T. Chen, G. B. Giannakis, and Q. Ling, “Rsa : Byzantine-robust stochastic aggregation methods for distributed learning from heterogeneous datasets,” 2018. [Online]. Available: https://api.semanticscholar.org/CorpusID:262982727
- P. Blanchard, E. M. E. Mhamdi, R. Guerraoui, and J. Stainer, “Machine learning with adversaries: Byzantine tolerant gradient descent,” in Neural Information Processing Systems, 2017. [Online]. Available: https://api.semanticscholar.org/CorpusID:28527385
- D. Yin, Y. Chen, K. Ramchandran, and P. L. Bartlett, “Byzantine-robust distributed learning: Towards optimal statistical rates,” in International Conference on Machine Learning, 2018. [Online]. Available: https://api.semanticscholar.org/CorpusID:3708326
- S. Li, E. C. H. Ngai, and T. Voigt, “An experimental study of byzantine-robust aggregation schemes in federated learning,” ArXiv, vol. abs/2302.07173, 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:256129862
- Yang Li (1142 papers)
- Chunhe Xia (9 papers)
- Chang Li (60 papers)
- Tianbo Wang (16 papers)