Does federated learning affect AI trust certification?

Federated learning does not change BorealisMark certification requirements. The BM Score evaluates behavioral outputs across five dimensions regardless of training methodology. However, federated learning makes bias auditing harder because training data cannot be directly inspected - a limitation that should be documented in the agent's model card.

AI Trust Glossary · Canonical Definition

Federated Learning

A machine learning approach where models are trained across decentralized devices without exchanging raw data, preserving privacy while enabling large-scale training.

Borealis Research Team · Updated March 2026 · View all 47 terms

Explanation

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.

Why it matters

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.

How Borealis uses it

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