پیوندهای مفید
اخبار و اعلانات
آمار
| تعداد نشریات | 31 |
| تعداد شمارهها | 834 |
| تعداد مقالات | 8,015 |
| تعداد مشاهده مقاله | 14,852,484 |
| تعداد دریافت فایل اصل مقاله | 9,586,508 |
Secure PDM: A Novel Byzantine Fault Tolerant Federated Learning Framework using a Robust PCA-Based Anomaly Detection Approach | ||
| International Journal of Industrial Electronics Control and Optimization | ||
| مقاله 10، دوره 8، شماره 4، اسفند 2025، صفحه 455-465 اصل مقاله (955.91 K) | ||
| نوع مقاله: Research Articles | ||
| شناسه دیجیتال (DOI): 10.22111/ieco.2025.51226.1668 | ||
| نویسندگان | ||
| Khalil Jahani1؛ Behzad Moshiri* 2؛ Babak Hossein Khalaj3 | ||
| 1Department of Computer Science, kish International Campus, University of Tehran, Tehran, Iran | ||
| 2School of ECE, College of Engineering, University of Tehran, Tehran, Iran | ||
| 3Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran | ||
| چکیده | ||
| With the proliferation of federated learning programs as a suitable framework for protecting user privacy and reducing the computational overhead of AI algorithms, various industries have also turned to the widespread use of this framework in industrial applications such as improving predictive maintenance (PDM). However, despite its increasing applications, several security challenges, such as Byzantine attacks, make the application of federated learning in industries questionable. Byzantine attacks in FL can degrade model performance by injecting malicious updates, causing model divergence or biased learning. This reduces accuracy, and can introduce security vulnerabilities such as backdoors. To address this problem, we propose a Byzantine Fault Tolerant (BFT) federated learning algorithm designed to improve PDM in industrial applications. Our proposed approach uses a PCA-based anomaly detection algorithm to detect and mitigate local Byzantine updates. Also, a game theory-based reward mechanism is designed to promote honest participation and discourage malicious behavior among federated users. The proposed framework is evaluated using the predictive maintenance datasets “AI4I 2020” and “NASA Acoustics and Vibration”. The results show that our proposed framework effectively detects and mitigates Byzantine attacks, enhancing the overall reliability of PDM in industrial applications. | ||
| کلیدواژهها | ||
| Federated Learning؛ byzantine fault tolerant؛ Predictive Maintenance؛ anomaly detection | ||
| مراجع | ||
|
[1] H. Brendan McMahan, E. Moore, D. Ramage, S. Hampson, B. Agüera y Arcas, "Communication-Efficient Learning of Deep Networks from Decentralized Data," Proceedings of the 20 th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017. JMLR: W&CP volume 54, last revised 26 Jan 2023 (v4), doi: https://doi.org/10.48550/arXiv.1602.05629.
[2] L. Li, Y. Fan, M. Tse, and K.-Y. Lin, "A review of applications in federated learning," Computers & Industrial Engineering, vol. 149, p. 106854, 2020, doi: https://doi.org/10.1016/j.cie.2020.106854. [3] J. Zhang, H. Zhu, F. Wang, J. Zhao, Q. Xu, and H. Li, "Security and Privacy Threats to Federated Learning: Issues, Methods, and Challenges," Security and Communication Networks, vol. 2022, no. 1, p. 2886795, 2022, doi: https://doi.org/10.1155/2022/2886795. [4] K. Jahani, B. Moshiri and B. Hossein Khalaj, “PPFL: Privacy-Preserving Techniques in Federated Learning”, JAIAI, vol. 1, no. 3, pp. 49–67, Jul. 2024, doi: 10.61838/jaiai.1.3.6. [5] Q. Xia, W. Ye, Z. Tao, J. Wu, and Q. Li, "A survey of federated learning for edge computing: Research problems and solutions," High-Confidence Computing, vol. 1, no. 1, p. 100008, 2021, doi: 10.1016/j.hcc.2021.100008. [6] J. Shi, W. Wan, S. Hu, J. Lu, L. Y. Zhang, "Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learning," vol. cs. CR,2022, doi: https://arxiv.org/abs/2112.14468. [7] A. Gouissem, K. Abualsaud, E. Yaacoub, T. Khattab and M. Guizani, "Federated Learning Stability Under Byzantine Attacks," 2022 IEEE Wireless Communications and Networking Conference (WCNC), Austin, TX, USA, 2022, pp. 572-577, doi: 10.1109/WCNC51071.2022.9771594. [8] M. Fang, X. Cao, J. Jia, and N. Z. Gong, "Local model poisoning attacks to byzantine-robust federated learning," in 29th USENIX Security Symposium, ed: USENIX Association, 2020, pp. 1623–1640. [9] T. Zhu Z. Guo, C. Yao, J. Tan, S. Dou, W. Wang, Z. Han, "Byzantine-robust Federated Learning via Cosine Similarity Aggregation," Computer Networks, vol. 254, p. 110730, 2024, doi: https://doi.org/10.1016/j.comnet.2024.110730. [10] P. Blanchard, E. M. El Mhamdi, R. Guerraoui, and J. Stainer, "Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent," NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems Pages 118 - 128, 2017. [11] D. Yin, Y. Chen, R. Kannan, and P. Bartlett, "ByzantineRobust Distributed Learning: Towards Optimal Statistical Rates," presented at the Proceedings of the 35th International Conference on Machine Learning, Proceedings of Machine Learning Research, 2018. [Online]. Available: https://proceedings.mlr.press/v80/yin18a.html. [12] Z. Li, H. Yu, T. Zhou, L. Luo, M. Fan, Z. Xu, G. Sun "Byzantine Resistant Secure Blockchained Federated Learning at the Edge," IEEE Network, vol. 35, no. 4, pp. 295–301, 2021, doi: 10.1109/MNET.011.2000604. [13] Y. Miao, Z. Liu, H. Li, K. K. R. Choo, and R. H. Deng, "Privacy-Preserving Byzantine-Robust Federated Learning via Blockchain Systems," IEEE Transactions on Information Forensics and Security, vol. 17, pp. 2848–2861, 2022, doi: 10.1109/TIFS.2022.3196274. [14] J. H. Chen, M. R. Chen, G. Q. Zeng, and J. S. Weng, "BDFL: A Byzantine-Fault-Tolerance Decentralized Federated Learning Method for Autonomous Vehicle," IEEE Transactions on Vehicular Technology, vol. 70, no. 9, pp. 8639–8652, 2021, doi: 10.1109/TVT.2021.3102121. [15] X. Luo and B. Tang, "Byzantine Fault-Tolerant Federated Learning Based on Trustworthy Data and Historical Information," Electronics, vol. 13, no. 8, 2024, doi: 10.3390/electronics13081540. [16] J. So, B. Güler, and A. S. Avestimehr, "Byzantine-Resilient Secure Federated Learning," IEEE Journal on Selected Areas in Communications, vol. 39, no. 7, pp. 2168–2181, 2021, doi: 10.1109/JSAC.2020.3041404. [17] X. Lin, Y. Li, X. Xie, Y. Ding, X. Wu, and C. Ge, "SFCABD: Secure Byzantine fault tolerance federated learning on Non-IID data," Knowledge-Based Systems, vol. 296, p. 111851, 2024, doi: https://doi.org/10.1016/j.knosys.2024.111851. [18] X. Tang, H. Gu, L. Fan, and Q. Yang, "Achieving Provable Byzantine Fault-tolerance in a Semi-honest Federated Learning Setting," in Advances in Knowledge Discovery and Data Mining, Cham, H. Kashima, T. Ide, and W.-C. Peng, Eds., 2023: Springer, https://doi.org/10.1007/978-3-031-33377-4_32. [19] Y. Tao, S. Cui, W. Xu, H. Yin, D. Yu, W. Liang, X. Cheng, "Byzantine-Resilient Federated Learning at Edge," IEEE Transactions on Computers, vol. 72, no. 9, pp. 2600–2614, 2023, doi: 10.1109/TC.2023.3257510. [20] N. Gupta, T. T. Doan, and N. Vaidya, "Byzantine FaultTolerance in Federated Local SGD Under 2f-Redundancy," IEEE Transactions on Control of Network Systems, vol. 10, no. 4, pp. 1669–1681, 2023, doi: 10.1109/TCNS.2023.3237489. | ||
|
آمار تعداد مشاهده مقاله: 415 تعداد دریافت فایل اصل مقاله: 241 |
||