StudyByteLearn
← SC-100: Microsoft Cybersecurity Architect
SC-100 · SaaS PaaS IaaS containers and AI services

Practice question 342 of 498 · hard

A design already uses scoped identities and private endpoints. Which two AI-specific controls provide complementary protection? Select two.

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

  1. A.Only an API rate limit with no prompt or model-interaction testing
  2. B.Only an additional private endpoint for a supporting service
  3. C.Layered input and output content filtering
  4. D.Only least-privilege service roles with no content analysis
  5. E.Adversarial testing and monitoring of suspicious AI usage
Show the answer and explanation

✓ Correct answers

  • Layered input and output content filtering
  • Adversarial testing and monitoring of suspicious AI usage

Layered content filtering and adversarial testing with monitoring address AI interaction threats beyond the existing identity and network controls. Another private endpoint or additional service-role scoping strengthens those same boundaries, while rate limits constrain volume. These alone do not detect malicious prompt content or test adversarial model behavior.

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.