Towards Robust Federated Learning: Investigating Poisoning Attacks Under Clients Data Heterogeneity
Document Type
Article
Publication Date
1-3-2025
Publication Title
2025 19th International Conference on Ubiquitous Information Management and Communication (IMCOM)
Publisher Name
IEEE
Abstract
Federated Learning (FL) offers a privacy-preserving solution by enabling multiple clients to train a shared model collaboratively without centralizing data. However, the decentralized nature of FL presents challenges, particularly regarding security and performance under adversarial conditions. This paper investigates the effects of poisoning attacks under data heterogeneity. Our experiments evaluate the impact of varying malicious client fractions and poison concentration levels on the accuracy of the model. We explore the effects of poisoning attacks on FedAvg and FedNova models using medical imaging tasks. Our findings reveal that increasing data heterogeneity exacerbates the effects of poisoning, with FedNova demonstrating greater resilience compared to FedAvg. We found that the number of malicious clients plays a more significant role in degrading performance than the ratio of poisoning samples shared by each malicious client, suggesting that even modest levels of poisoning can be tolerated by most algorithms. The study highlights the importance of developing robust defense mechanisms to maintain model performance under adversarial conditions.
Recommended Citation
A. Soubih, S. A. Lahmer, M. Abuhamad and T. Abuhmed, "Towards Robust Federated Learning: Investigating Poisoning Attacks Under Clients Data Heterogeneity," 2025 19th International Conference on Ubiquitous Information Management and Communication (IMCOM), Bangkok, Thailand, 2025, pp. 1-8, doi: 10.1109/IMCOM64595.2025.10857574.
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Copyright Statement
© IEEE, 2025.
Comments
Author Posting © 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The definitive version was published in 2025 19th International Conference on Ubiquitous Information Management and Communication (IMCOM) (January 2025), https://doi.org/10.1109/IMCOM64595.2025.10857574.