Model-level privacy

https://taxonomy.eticas.ai/risk/privacy-model-level

Risks from AI models leaking or exposing private information through their outputs or structure.

Mappings to external frameworks

Framework	Concept
MIT AI Risk Repository	Compromise of privacy by obtaining, leaking or inferring sensitive information
W3C Data Privacy Vocabulary — AI Extension	Membership Inference Attack

OpenAI Privacy Filter _[tool] Open-source tool for detecting and filtering personally identifiable information in LLM inputs and outputs.

Part of the Eticas AI Risk Taxonomy. URI: https://taxonomy.eticas.ai/risk/privacy-model-level