Menu for AI & Cybersecurity
Courses and project AI & Cybersecurity
On this page

Part 4 exercises · Adversarial machine learning

All exercises · Part 3 · Part 5

How do attackers fool a frozen model, or teach a retrained one? About 25 minutes. Work through the exercises in order; the last one is a short scenario that combines them.

What you will practise

  • Describe an attacker by goal, knowledge, capability and stage
  • Place an attack by lifecycle stage and violated property
  • Play the attacker against a frozen phishing detector
  • Say what a robustness claim covers
  • Follow a report on its way to becoming a label, and order the release gates

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.

These exercises need JavaScript. The slides and the companion pages work without it.