Part 6 exercises · Securing AI systems in practice

All exercises · Part 5

Slides: Parts 4–6 slides

Which controls make an AI system defensible, and what evidence shows it? About 20 minutes. Work through the exercises in order; the last one is a short scenario that combines them.

What you will practise

• Map a case to MITRE ATLAS and find coverage
• Connect an asset to a named owner
• Decide where authority stops for a hospital triage agent
• Stop information leaving, and trace every value in a summary
• Choose the right framework or standard for the question
• Decide what to retest when a release adds a tool

Every exercise gives you feedback after you try, and names the slide to look at. You can retry as often as you like, ask for hints, and see the answer after a failed attempt. Your progress is saved only in this browser and is never sent anywhere.