Open access
2026
AMBER: Robust Federated Learning Based on Client Verification
This paper analyzes client-side vulnerabilities in three chained stages of local training: local dataset pollution, model selective inputs, and training process tampering and proposes AMBER, a robust FL framework with a novel three-layer verification mechanism for client trust assessment.
Xiaohu Shan, Haiyang Yu, Gang Wang et al.
· IEEE Transactions on Informa... · 0 citations