StudyByteLearn
← SC-100: Microsoft Cybersecurity Architect
SC-100 · Data classification encryption databases and storage

Practice question 467 of 498 · medium

Which two measures directly protect an AI retrieval boundary? Select two.

Select all that apply. Every correct option and no extras are required for credit in the app.

  1. A.Use response formatting as the sole confidentiality control
  2. B.Trust any user-supplied group identifier
  3. C.Enforce supported access checks or trusted security filters before content enters grounding
  4. D.Preserve appropriate document permission metadata during ingestion
  5. E.Let the model decide each user's legal permissions after reading all documents
Show the answer and explanation

✓ Correct answers

  • Enforce supported access checks or trusted security filters before content enters grounding
  • Preserve appropriate document permission metadata during ingestion

Permission metadata and trusted retrieval enforcement establish the boundary. Post-retrieval model judgment, arbitrary caller groups, and response formatting do not provide reliable authorization.

Read the source reference

Read and review here, or open the app to practise and save your results on this device.

Practise in the app

Unofficial study material. Not affiliated with or endorsed by Microsoft. These are original learning questions, not actual exam questions. Product capabilities and exam objectives can change; verify current Microsoft documentation. Practice scores do not predict or guarantee an exam result.