Apply the Privacy-Aware ML curriculum to a checked project.
Project brief
Required concepts
- Privacy-aware ML: threat model, data minimization and purpose
- Privacy units and bounded contribution: count people, not events
- Private aggregate releases: sensitivity, budget and query control
- Federated training: local data, update leakage and aggregation boundaries
- Model leakage evaluation: membership risk, memorization and limits
- Privacy operations: deletion lineage, access gates and release review
Completion standard
Submit runnable work, a data manifest, measured results and failure-case evidence.