International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Federated Learning Poisoning Attack Detection: Reconfiguration Algorithm Top K-FL Credit |
|---|---|
| ABSTRACT | Federated Learning (FL) allows for cooperative model training without exchanging raw data, but it is nevertheless susceptible to poisoning assaults, in which malevolent players introduce tainted updates to deteriorate the overall performance of the model [1]. A more robust defense framework is presented in this study. The Top K-FLcredit Reconfiguration Algorithm combines a dynamic credit-based trust scoring system with Top-K gradient filtering. Depending on the regularity and caliber of their contributions, clients can gain or lose credit, which enables the server to isolate or downweight questionable users [9]. The technique successfully reduces attempts to poison data and models while preserving high accuracy by combining selective gradient aggregation with ongoing trust assessment [3]. |
| AUTHOR | G C DIVYA, MOKSHA B V, NITYA SHREE R H, SPOORTHI A C, TEJASWINI H Assistant Professor, Dept. of CSE, Jain Institute of Technology, Davangere, India 7th Semester, Dept. of CSE, Jain Institute of Technology, Davangere, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312111 |
| pdf/111_Federated Learning Poisoning Attack Detection Reconfiguration Algorithm Top K-FL Credit.pdf | |
| KEYWORDS | |
| References | 1. L. Zhao, S. Li, and Q. Yang, "Privacy-preserving and attack- resistant federated learning: A survey," IEEE Internet of Things Journal, vol. 9, no. 12, pp. 60–79, 2022. 2. FLGuard: Byzantine-resilient safe aggregation in federated learning, H. Sun, Z. Du, and H. Liu, IEEE Transactions on Dependable and safe Computing, vol. 19, no. 5, pp. 55–69, 2022. 3. "How to backdoor federated learning," E. Bagdasaryan, A. Veit, Y. Hua, D. Oestrin, and V. Shmatikov, Proceedings of AISTATS, pp. 45–57, 2022. 4. "Local model poisoning attacks to federated learning," by M. Fang, X. Cao, J. Jia, and N. Gong, Proceedings of the USENIX Security Symposium, pp. 12–28, 2022. 5. "Secure federated learning framework for data poisoning attack defence," W. Gao, J. Liu, and K. Xu, IEEE Access, vol. 10, pp. 76–91, 2022. 6. X. Xie, K. Huang, and Z. Zhang, “Credit‐score based trust evaluation in federated learning,” IEEE Transactions on Network Science and Engineering, vol. 11, no. 1, pp. 72–90, 2023. 7. K. Zhang and L. Wu, “Detection of data poisoning using credit reconfiguration,” in Proc. IEEE Big Data, pp. 25– 41, 2023. 8. J. He, M. Tao, and W. Zeng, “AI‐ enabled poisoning attack detection in federated learning,” IEEE Access, vol. 12, pp. 15–28, 2023. 9. Backdoor assaults and defences in federated learning, N. Wang and Y. Chen, Expert Systems with Applications, vol. 228, pp. 1–16, 2023. 10. Electronics, vol. 12, no. 2, pp. 1–29, 2023; A. Rahman and M. Islam, "A survey on federated learning poisoning attacks and defences." Federated optimisation in heterogeneous networks, T. Li, A. Sahu, and V. Smith, in Proceedings of MLSys, pp. 80– 99, 2023 11. P. Kairouz et al., “Advances and open problems in federated learning,” Foundations and Trends in Machine Learning, vol. 14, no. 1–2, pp. 1–210, 2023. 12. IEEE Transactions on Mobile Computing, vol. 23, no. 4, pp. 2001–2015, 2024; M. Huang, L. Xiao, and H. Dai, "Robust aggregation against poisoning attacks in federated learning." 13. V. K. Sharma and R. Sing, “Secure aggregation using scoring‐based anomaly isolation in FL,” IEEE Access, vol. 13, pp. 30–49, 2024. 14. "Federated poisoning attack detection using adaptive defence," IEEE Transactions on Information Forensics and Security, vol. 19, pp. 521–533, 2024, M. Fang, X. Cao, and N. Gong. 15. S. Gupta and P. Singh, “Federated learning for cybersecurity: Emerging threats and defences,” Applied Sciences, vol. 14, no. 11, pp. 1–14, 2024. |
