How to meet it
OWASP AISVS v1.01
Access Control & Identity for AI Components & Users · AI Resource Authorization & Classification
Filter out data the user may not see
Verify that post-inference filtering mechanisms prevent responses from including data that the requester is not authorized to receive.
OWASP AISVS v1.01, requirement 5.2.4
In plain English
Check the answer before it leaves, and remove any data the person asking is not allowed to see, as a backstop to the checks made during retrieval.
What good looks like
- Responses are checked against the requester's permissions before delivery.
- Restricted data found in a response is removed or the response is blocked.
- Blocks are logged.
How teams usually do it
- An output filter that compares cited sources with the user's permissions.
- Pattern checks for data types the user should never receive.
Evidence an auditor would accept
- Filter configuration and test cases.
Common mistakes
- Assuming retrieval filters catch everything, when the model may repeat data from earlier in the conversation or from memory.
Not sure which requirements apply to your system? Take the assessment.
Requirement text from the OWASP AI Security Verification Standard, licensed under CC BY-SA 4.0. This guidance is shared under the same licence.