A Byzantine-Resilient Aggregation Scheme for Federated Learning via Matrix Autoregression on Client Updates. (arXiv:2303.16668v1 [cs.LG])

In this work, we propose FLANDERS, a novel federated learning (FL)
aggregation scheme robust to Byzantine attacks. FLANDERS considers the local
model updates sent by clients at each FL round as a matrix-valued time series.
Then, it identifies malicious clients as outliers of this time series by
comparing actual observations with those estimated by a matrix autoregressive
forecasting model. Experiments conducted on several datasets under different FL
settings demonstrate that FLANDERS matches the robustness of the most powerful
baselines against …

aggregation attacks baselines client clients datasets federated learning forecasting local malicious matrix novel robustness series settings under updates work