Part 5 exercises · Privacy, supply chain and LLM applications

All exercises · Part 4 · Part 6

Slides: Parts 4–6 slides

What can a model leak, and what happens when it reads untrusted text? About 25 minutes. Work through the exercises in order; the last one is a short scenario that combines them.

What you will practise

• Name the privacy attack and work out what a membership score means
• Match supply-chain links with their controls
• Find the injected instruction in a reported email
• Show why a proposal still needs permission outside the model
• Remove a capability and name the cost

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.