https://taxonomy.eticas.ai/risk/privacy-model-level
Risks from the model exposing personal or confidential information through its outputs.
| Framework | Reference |
|---|---|
| MIT AI Risk Repository | Compromise of privacy by obtaining, leaking or correctly inferring sensitive information |
| AIR 2024 | Model attacks (membership inference, model inversion) |
| W3C Data Privacy Vocabulary — AI Extension | Model Inversion |