Skip to content
AI Security

Interview question · How LLM Systems Work

How does NIST AI 100-2 classify adversarial machine learning attacks, and why does a shared taxonomy help?

A framework question that rewards structure. The scored answer gives the axes NIST uses, places familiar attacks on them, and shows how a shared vocabulary changes real work.

mediumNewPreparation tags: Microsoft, Google, AmazonUpdated Nov 2026

A framework question that rewards structure. The scored answer gives the axes NIST uses, places familiar attacks on them, and shows how a shared vocabulary changes real work.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 529 remaining answers · $25

Every worked answer in all 17 topics, every lesson in every course, the full concept curriculum, the complete practice-test bank, and the downloadable security field guides.

6 months · One payment · No auto-renewal

What if · the follow-ups in this answer

The answer works through 6 follow-ups like an interviewer would

A new AI security team keeps arguing over what 'poisoning', 'evasion' and 'jailbreak' mean, and someone suggests adopting NIST AI 100-2 as the shared vocabulary.

  1. What is NIST AI 100-2?
  2. How is the taxonomy organised?
  3. How would you classify a poisoned document in a RAG index?
  4. What does it not give you?
  5. What if a vendor claims its product 'stops adversarial attacks'?
  6. How would you use it in the team?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Premium opens every answer and ladder.

UP NEXT ON YOUR JOURNEY
Next in this trackWhat is the difference between abuse of an AI system and compromise of it?Next in this trackBeyond prompt injection, what security problems come with accepting images, audio and documents?Next in this trackWhat changes for security when an application uses a reasoning model that thinks before it answers?
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.