Each participant trains on local data and shares only model updates (gradients), not the underlying data. A central server aggregates updates to improve a shared model. This enables training on sensitive datasets (medical records, financial transactions) without centralizing that data.

Federated learning changes data provenance dynamics. Training data never leaves its source, reducing compliance burden. But it also makes bias auditing harder - if you cannot see the training data, you cannot audit it directly.

Federated learning does not change certification requirements. The BTS evaluates behavioral outputs regardless of training methodology. The audit focuses on behavior, not training approach.