Conference
Sep 2026
Exploiting Feature Non-IIDness for Untargeted Data Poisoning Attacks in Byzantine-Robust Federated Learning
This paper identifies and exploits feature non-IIDness, demonstrating that by manipulating only the features of local data on compromised clients, adversaries can generate malicious updates to bypass RA rules and significantly degrade the global model’s performance.
Jun-Zhe Huang, Chong-Qi Guan, Guo-Hong Cao
· IEEE Conference on Communica... · 0 citations