MAD-Based Update Filtering for Non-IID Federated Learning: Robustness Analysis Under Poisoning Attacks
IEEE Access · 2026 · 14 · 118452-118463
DOI: 10.1109/access.2026.3719290 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Tae-Wook Kang und 6 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea (NRF) grant funded by Korean Government.
Abstract (Originalsprache)
Federated Learning enables collaborative model training without sharing raw client data, making it attractive for privacy-sensitive domains. However, its performance degrades when local data are non-independent and identically distributed (non-IID) and when malicious clients inject adversarial updates; robust aggregation alone can be insufficient, especially for imbalanced medical datasets where minority-class degradation is masked by overall accuracy. This paper proposes a Median Absolute Deviation (MAD)-based malicious-update filtering framework for non-IID federated learning. The server flags and excludes abnormal client updates before aggregation, using a coordinate-wise median reference and a modified Z-score over cosine distances. Unlike trust-based defenses, it requires no clean server-side dataset and provides an interpretable, per-round diagnostic. We evaluate it on CIFAR-10 and HAM10000 under noise injection and sign flipping against eight robust aggregation baselines, under a unified protocol that reports Accuracy and Macro-F1 at the same validation-selected checkpoint, averaged over three seeds. On CIFAR-10, the proposed method attains a mean Macro-F1 comparable to or better than the strongest baselines under both attacks (75.9% and 67.6%). On HAM10000 under noise injection it achieves the highest mean accuracy (74.0%) with a competitive Macro-F1, whereas under sign flipping it is only mid-ranked. An ablation indicates that removing MAD filtering substantially reduces class-balanced performance on HAM10000 under noise injection, and a diagnostic analysis shows that the cosine-distance signal separates benign and malicious updates strongly under noise injection but weakly under sign flipping. These results characterize both the robustness potential and the boundary conditions of update-level median filtering in non-IID federated learning.
Förderung
- National Research Foundation of Korea (NRF) grant funded by Korean Government
Zitieren
APA
Kang, T., Park, J., Park, C., Sim, C., Jung, S., Lee, H., & Shin, C. (2026). MAD-Based Update Filtering for Non-IID Federated Learning: Robustness Analysis Under Poisoning Attacks. IEEE Access, 14, 118452-118463. https://doi.org/10.1109/access.2026.3719290
Vancouver
Kang T, Park J, Park C, Sim C, Jung S, Lee H, et al. MAD-Based Update Filtering for Non-IID Federated Learning: Robustness Analysis Under Poisoning Attacks. IEEE Access. 2026;14:118452-118463. doi:10.1109/access.2026.3719290
BibTeX
@article{Kang2026,
author = {Kang, Tae-Wook and Park, Ji-Woo and Park, Chul-Young and Sim, Chun-Bo and Jung, Se-Hoon and Lee, Han-Sung and Shin, Chang-Sun},
title = {MAD-Based Update Filtering for Non-IID Federated Learning: Robustness Analysis Under Poisoning Attacks},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {118452--118463},
doi = {10.1109/access.2026.3719290}
}
EUVIMED