Byzantine-Robust Federated Learning Defense

Federated learning trains one shared model from many clients' local gradient updates without ever centralizing their raw data — but that also means the server must trust updates it cannot inspect. This simulator renders six clients orbiting a central global model in 3D: each round every client sends a local update, one or more can be set malicious and send a poisoned update scaled away from the shared true optimum, and the server aggregates all six into the next model position. Switch the aggregation rule between a naive mean — which a single unbounded malicious update can drag anywhere — and a Byzantine-robust coordinate-wise median, which outvotes a minority of poisoned updates instead of averaging them in, while live readouts track the model's distance from the true optimum and the measured poisoning impact on the aggregate each round.