Researchers developed a classification system of privacy preferences for artificial intelligence agents
Researchers developed a classification system of privacy preferences that can be enforced in systems where artificial intelligence agents perform actions independently for users.
The researchers examined 30 leading AI assistants and agent platforms as part of their study.
The researchers created eight open-source prototypes demonstrating how privacy preference controls can be built into agentic protocols including the Model Control Protocol and Agent2Agent protocol.
Sources behind this report
Report history
No earlier revision dates are retained here. This does not establish that the report has never changed; read any dated updates and corrections.
This brief was made by AI and checked against its cited public sources. How the newsroom works