ARFED: Attack-Resistant Federated averaging based on outlier elimination. (arXiv:2111.04550v2 [cs.LG] UPDATED)

In federated learning, each participant trains its local model with its own
data and a global model is formed at a trusted server by aggregating model
updates coming from these participants. Since the server has no effect and
visibility on the training procedure of the participants to ensure privacy, the
global model becomes vulnerable to attacks such as data poisoning and model
poisoning. Although many defense algorithms have recently been proposed to
address these attacks, they often make strong assumptions …

attack coming data federated learning global local own privacy procedure server training trains updates visibility