Open access
2026
MAD-Based Update Filtering for Non-IID Federated Learning: Robustness Analysis Under Poisoning Attacks
A 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.
Tae-Wook Kang, Ji-Woo Park, Chulyoung Park et al.
· IEEE Access · 0 citations