Model Hijacking Attack in Federated Learning
Published in IEEE Transactions on Information Forensics and Security (TIFS), 2026
This paper exposes a critical vulnerability in federated learning protocols where adversarial clients manipulate aggregation dynamics to hijack the global model behavior.
Recommended citation: Z Li, S Wu, R Chen, P Aditya, IE Akkus, M Vanga, M Zhang, H Li*, Y Zhang. (2026). "Model Hijacking Attack in Federated Learning." IEEE TIFS.