A TRUST-BASED INCENTIVE FRAMEWORK FOR FEDERATED LEARNING IN EDGE ENVIRONMENTS WITH DIVERSE PARTICIPANTS
Keywords:
Federated Learning, Edge Computing, Incentive Mechanism, Trust ManagementAbstract
Federated Learning (FL) offers a privacy-preserving paradigm for collaborative model training, particularly well-suited for edge computing. However, the inherent heterogeneity of edge clients—encompassing data distribution, computational capabilities, and reliability—poses significant challenges to FL's effectiveness, including performance degradation and vulnerability to malicious participants. This article proposes a novel trust-based incentive mechanism designed to address these issues by dynamically evaluating client trustworthiness and adjusting incentives accordingly. Our framework integrates a multi-faceted trust score that considers contribution quality, reliability, and the detection of malicious behavior. By rewarding trustworthy contributions and penalizing unreliable actions, the proposed mechanism aims to enhance global model accuracy, improve robustness against attacks, and foster fairness among diverse participants. This approach encourages consistent, high-quality contributions while mitigating risks from untrustworthy clients, paving the way for more resilient and efficient federated learning deployments in real-world edge environments.
References
1. Aminifar, A.; Shokri, M.; Aminifar, A. Privacy-preserving edge federated learning for intelligent mobile-health systems. Future Gener. Comput. Syst. 2024, 161, 625–637.
2. Lazaros, K.; Koumadorakis, D.E.; Vrahatis, A.G.; Kotsiantis, S. Federated Learning: Navigating the Landscape of Collaborative Intelligence. Electronics 2024, 13, 4744.
3. Ivanovic, M. Influence of Federated Learning on Contemporary Research and Applications. In Proceedings of the 2024 International Conference on INnovations in Intelligent SysTems and Applications (INISTA), Craiova, Romania, 4–6 September 2024; IEEE: Piscataway, NJ, USA, 2024; pp. 1–6.
4. Iyer, V.N. A review on different techniques used to combat the non-IID and heterogeneous nature of data in FL. arXiv 2024, arXiv:2401.00809.
5. Hartmann, M.; Danoy, G.; Bouvry, P. FedPref: Federated Learning Across Heterogeneous Multi-objective Preferences. ACM Trans. Model. Perform. Eval. Comput. Syst. 2024, 10, 1–40.
6. Chen, Y. Advancing Federated Learning by Addressing Data and System Heterogeneity. In Proceedings of the AAAI Symposium Series, Stanford, CA, USA, 25–27 March 2024; Volume 3, p. 294.
7. Liu, C.; Alghazzawi, D.M.; Cheng, L.; Liu, G.; Wang, C.; Zeng, C.; Yang, Y. Disentangling Client Contributions: Improving Federated Learning Accuracy in the Presence of Heterogeneous Data. In Proceedings of the 2023 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), Wuhan, China, 21–24 December 2023; IEEE: Piscataway, NJ, USA, 2023; pp. 381–387.
8. Taghiyarrenani, Z.; Alabdallah, A.; Nowaczyk, S.; Pashami, S. Heterogeneous Federated Learning via Personalized Generative Networks. arXiv 2023, arXiv:2308.13265.
9. Ma, C.; Li, J.; Ding, M.; Wei, K.; Chen, W.; Poor, H.V. Federated learning with unreliable clients: Performance analysis and mechanism design. IEEE Internet Things J. 2021, 8, 17308–17319.
10. Xia, G.; Chen, J.; Huang, X.; Yu, C.; Zhang, Z. FL-PTD: A Privacy Preserving Defense Strategy Against Poisoning Attacks in Federated Learning. In Proceedings of the 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC), Torino, Italy, 26–30 June 2023; IEEE: Piscataway, NJ, USA, 2023; pp. 735–740.
11. Manzoor, H.U.; Shabbir, A.; Chen, A.; Flynn, D.; Zoha, A. A survey of security strategies in federated learning: Defending models, data, and privacy. Future Internet 2024, 16, 374.
12. Zhang, H.; Elsayed, M.; Bavand, M.; Gaigalas, R.; Ozcan, Y.; Erol-Kantarci, M. Federated learning with dual attention for robust modulation classification under attacks. In Proceedings of the ICC 2024-IEEE International Conference on Communications, Denver, CO, USA, 9–13 June 2024; IEEE: Piscataway, NJ, USA, 2024; pp. 5238–5243.
13. Wang, T.; Zheng, Z.; Lin, F. Federated learning framework based on trimmed mean aggregation rules. Expert Syst. Appl. 2025, 270, 126354.
14. Nabavirazavi, S.; Taheri, R.; Shojafar, M.; Iyengar, S.S. Impact of aggregation function randomization against model poisoning in federated learning. In Proceedings of the 22nd IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2023, Exeter, UK, 1–3 November 2023; Institute of Electrical and Electronics Engineers Inc.: Piscataway, NJ, USA, 2024; pp. 165–172.
15. Xiong, A.; Chen, Y.; Chen, H.; Chen, J.; Yang, S.; Huang, J.; Li, Z.; Guo, S. A truthful and reliable incentive mechanism for federated learning based on reputation mechanism and reverse auction. Electronics 2023, 12, 517.
16. Han, K.; Zhang, G.; Yang, L.; Bai, J. Client dependability evaluation in federated learning framework. In Proceedings of the Third International Conference on Communications, Information System, and Data Science (CISDS 2024), Nanjing, China, 22–24 November 2024; SPIE: Bellingham, WA, USA, 2025; Volume 13519, pp. 71–79.
17. Chen, Z.; Zhang, H.; Li, X.; Miao, Y.; Zhang, X.; Zhang, M.; Ma, S.; Deng, R.H. FDFL: Fair and discrepancy-aware incentive mechanism for federated learning. IEEE Trans. Inf. Forensics Secur. 2024, 19, 8140–8154.
18. Wu, R.; Chen, Y.; Tan, C.; Luo, Y. MDIFL: Robust federated learning based on malicious detection and incentives. Appl. Sci. 2023, 13, 2793.
19. Yellampalli, S.S.; Chalupa, M.; Wang, J.; Song, H.J.; Zhang, X.; Yue, H.; Pan, M. Client Selection in Federated Learning: A Dynamic Matching-Based Incentive Mechanism. In Proceedings of the 2024 International Conference on Computing, Networking and Communications (ICNC), Big Island, HI, USA, 19–24 February 2024; IEEE: Piscataway, NJ, USA, 2024, pp. 989–993.
20. Han, J.; Khan, A.F.; Zawad, S.; Anwar, A.; Angel, N.B.; Zhou, Y.; Yan, F.; Butt, A.R. Tiff: Tokenized incentive for federated learning. In Proceedings of the 2022 IEEE 15th International Conference on Cloud Computing (CLOUD), Barcelona, Spain, 10–16 July 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 407–416.
21. Wenya, L.; Bo, L.; Weiwei, L.; Yuanchao, Y. Survey of incentive mechanism for federated learning. Comput. Sci. 2022, 49, 7.
22. Ling, X.; Li, R.; Ouyang, T.; Chen, X. Time is Gold: A Time-Dependent Incentive Mechanism Design for Fast Federated Learning. In Proceedings of the 2022 IEEE/CIC International Conference on Communications in China (ICCC), Foshan, China, 11–13 August 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 1038–1043.
23. Zhou, Y. A Survey of Incentive Mechanisms for Federated Learning. Appl. Comput. Eng. 2024, 10, 1035–1044.
24. Zhang, W.; Wang, Q.; Zhao, H.; Xia, W.; Zhu, H. Incentivizing Quality Contributions in Federated Learning: A Stackelberg Game Approach. In Proceedings of the 2024 IEEE 99th Vehicular Technology Conference (VTC2024-Spring), Singapore, 24–27 June 2024; IEEE: Piscataway, NJ, USA, 2024; pp. 1–5.
25. Huang, J.; Hong, C.; Chen, L.Y.; Roos, S. Is shapley value fair? improving client selection for mavericks in federated learning. arXiv 2021, arXiv:2106.10734.
26. Xia, H.; Li, X.; Pang, J.; Liu, J.; Ren, K.; Xiong, L. P-Shapley: Shapley Values on Probabilistic Classifiers. Proc. VLDB Endow. 2024, 17, 1737–1750.
27. Pang, J.; Yu, J.; Zhou, R.; Lui, J.C.S. An Incentive Auction for Heterogeneous Client Selection in Federated Learning. IEEE Trans. Mob. Comput. 2023, 22, 5733–5750.
28. Al-Saedi, A.A. Contribution prediction in federated learning via client behavior evaluation. Future Gener. Comput. Syst. 2024, 166, 107639.
29. Ma, S.; Liu, H.; Wang, N.; Xie, H.; Huang, L.; Li, H. Deep reinforcement learning for an incentive-based demand response model. In Proceedings of the 2022 IEEE 6th Conference on Energy Internet and Energy System Integration (EI2), Chengdu, China, 11–13 November 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 246–250.
30. Casalicchio, E.; Esposito, S.; Al-Saedi, A.A. FLWB: A Workbench Platform for Performance Evaluation of Federated Learning Algorithms. In Proceedings of the 2023 IEEE International Workshop on Technologies for Defense and Security (TechDefense), Rome, Italy, 20–22 November 2023.
31. Hsu, C.F.; Huang, J.L.; Liu, F.H.; Chang, M.C.; Chen, W.C. Fedtrust: Towards building secure robust and trustworthy moderators for federated learning. In Proceedings of the 2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR), Virtual, 2–4 August 2022; IEEE: Piscataway, NJ, USA, 2022; pp. 318–323.
32. Zhang, X.; Li, F.; Zhang, Z.; Li, Q.; Wang, C.; Wu, J. Enabling execution assurance of federated learning at untrusted participants. In Proceedings of the IEEE INFOCOM 2020-IEEE Conference on Computer Communications, Virtual, 6–9 July 2020; IEEE: Piscataway, NJ, USA, 2020; pp. 1877–1886.
33. Lyubchyk, L.; Grinberg, G.; Konokhova, Z.; Yamkovyi, K. Composite Indicators Building Based on Concordant of Expert-Statistical Information Using Biased Ridge Kernel Regression. In Proceedings of the 2023 IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Dortmund, Germany, 7–9 September 2023; IEEE: Piscataway, NJ, USA, 2023; Volume 1, pp. 617–620.
34. Yang, H.; Gu, D.; He, J. A robust and efficient federated learning algorithm against adaptive model poisoning attacks. IEEE Internet Things J. 2024, 11, 16289–16302.
35. Yazdinejad, A.; Dehghantanha, A.; Karimipour, H.; Srivastava, G.; Parizi, R.M. A robust privacy-preserving federated learning model against model poisoning attacks. IEEE Trans. Inf. Forensics Secur. 2024, 19, 6693–6708.
36. Perry, S.; Jiang, Y.; Zhong, F.; Huang, J.; Gyawali, S. DynaDetect2.0: Improving Detection Accuracy of Data Poisoning Attacks. In Proceedings of the 2024 Cyber Awareness and Research Symposium (CARS), Grand Forks, ND, USA, 28–29 October 2024; IEEE: Piscataway, NJ, USA, 2024; pp. 1–8.
37. Abri, F.; Zheng, J.; Namin, A.S.; Jones, K.S. Markov decision process for modeling social engineering attacks and finding optimal attack strategies. IEEE Access 2022, 10, 109949–109968.
38. Malik, P.; Alirajpurwala, T.; Kaushal, S.; Patidar, T.; Indore, I.I.I.; Padlak, S. Scalability and robustness of federated learning systems: Challenges and solutions. Int. J. Sci. Res. Eng. Manag. IJSREM 2024, 8.
39. Abdelmoniem, A.M.; Ho, C.Y.; Papageorgiou, P.; Canini, M. A comprehensive empirical study of heterogeneity in federated learning. IEEE Internet Things J. 2023, 10, 14071–14083.
40. Abdelmoniem, A.M.; Ho, C.Y.; Papageorgiou, P.; Canini, M. Empirical analysis of federated learning in heterogeneous environments. In Proceedings of the 2nd European Workshop on Machine Learning and Systems, Rennes France, 5–8 April 2022; pp. 1–9.
41. Yu, X.; He, Z.; Sun, Y.; Xue, L.; Li, R. The Effect of Personalization in FedProx: A Fine-grained Analysis on Statistical Accuracy and Communication Efficiency. arXiv 2024, arXiv:2410.08934.
42. Kang, H.; Kim, M.; Lee, B.; Kim, H. FedAND: Federated learning exploiting consensus ADMM by nulling drift. IEEE Trans. Ind. Inform. 2024, 20, 9837–9849.
43. Mahmoud, M.H.; Albaseer, A.; Abdallah, M.; Al-Dhahir, N. Federated learning resource optimization and client selection for total energy minimization under outage, latency, and bandwidth constraints with partial or no CSI. IEEE Open J. Commun. Soc. 2023, 4, 936–953.
44. Antonioli, D.; Tippenhauer, N.O.; Rasmussen, K. Bias: Bluetooth impersonation attacks. In Proceedings of the 2020 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA, 18–20 May 2020; IEEE: Piscataway, NJ, USA, 2020; pp. 549–562.
45. Ebrahimabadi, M.; Lalouani, W.; Younis, M.; Karimi, N. Countering PUF modeling attacks through adversarial machine learning. In Proceedings of the 2021 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), Tampa, FL, USA, 7–9 July 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 356–361.
46. Wang, B.; Sun, S.; Ren, W. Distributed continuous-time algorithms for optimal resource allocation with time-varying quadratic cost functions. IEEE Trans. Control Netw. Syst. 2020, 7, 1974–1984.
47. Javaherian, S.; Turney, B.; Chen, L.; Tzeng, N.F. Incentive-Compatible Federated Learning with Stackelberg Game Modeling. arXiv 2025, arXiv:2501.02662.
48. Collins, L.; Hassani, H.; Mokhtari, A.; Shakkottai, S. Fedavg with fine tuning: Local updates lead to representation learning. Adv. Neural Inf. Process. Syst. 2022, 35, 10572–10586.
49. Mora, A.; Bujari, A.; Bellavista, P. Enhancing generalization in federated learning with heterogeneous data: A comparative literature review. Future Gener. Comput. Syst. 2024, 157, 1–15.
50. Chakravarthy, V.; Bell, D.; Bhaskaran, S. Emergent Intrusion Detection System for Fog Enabled Smart Agriculture Using Federated Learning and Blockchain Technology: A Review. In Proceedings of the 2024 International Conference on IT Innovation and Knowledge Discovery (ITIKD), Manama, Bahrain, 13–15 April 2025; IEEE: Piscataway, NJ, USA, 2025; pp. 1–7.
51. Yang, K.; Imam, N. Secure and Private Federated Learning: Achieving Adversarial Resilience through Robust Aggregation. arXiv 2025, arXiv:2505.17226.