Evidence · DiggingBeagle record
Contextual integrity of agent data disclosures
An assistant can correctly recognize that a piece of private data is needed to complete a task yet fail the separate question of whether the requester is entitled to receive it. The contextual-integrity experiments separated genuine need from requester authority and reported frequent disclosure in Type III scenarios across synthetic bank, identity and address examples. Small samples and artificial data limit generalization. Research/disclosure claims are specific to the documented settings; do not infer unreported victims or additional compromise.
- Source role
- primary disclosure
Evidence record
An assistant can correctly recognize that a piece of private data is needed to complete a task yet fail the separate question of whether the requester is entitled to receive it. The contextual-integrity experiments separated genuine need from requester authority and reported frequent disclosure in Type III scenarios across synthetic bank, identity and address examples. Small samples and artificial data limit generalization. Research/disclosure claims are specific to the documented settings; do not infer unreported victims or additional compromise.
Claim-level citations (2)
- supportsAgent privacy tests separate legitimate task data needs from requester authority: The contextual-integrity experiments separated genuine need from requester authority and reported frequent disclosure in Type III scenarios across synthetic bank, identity and address examples. Small samples and artificial data limit generalization.
Contextual integrity experiment: Type III versus Type IV disclosure
- supportsAgent privacy tests separate legitimate task data needs from requester authority: An assistant can correctly recognize that a piece of private data is needed to complete a task yet fail the separate question of whether the requester is entitled to receive it.
Contextual integrity experiment: Type III versus Type IV disclosure