AISG practice · Module 5

Model Security & the Secure AI Lifecycle — 10 questions. Choose the BEST answer.

You can answer as a guest, but you'll need a free account to see your score and save it. Sign up · Sign in
Question 1 Question 1 · M5
Which API design change MOST reduces the information available for extraction?
Question 2 Question 2 · M5
An assistant generates SQL and executes it with an admin database role. What is the MOST important fix?
Question 3 Question 3 · M5
Which technique identifies whether a suspect model derives from yours without modifying your model?
Question 4 Question 4 · M5
What does an approved model registry enforce that a simple file store does not?
Question 5 Question 5 · M5
Which OWASP risk covers model output that leads to XSS or command injection downstream?
Question 6 Question 6 · M5
A model file is copied directly onto a production server, bypassing the registry. Which control would have stopped it from running?
Question 7 Question 7 · M5
What does verifying a signature at model load time protect against?
Question 8 Question 8 · M5
Why should system prompts and tool definitions be treated as confidential but never as secret stores?
Question 9 Question 9 · M5
Which control MOST directly prevents one noisy tenant from starving others on a shared inference service?
Question 10 Question 10 · M5
Why must evaluation jobs and test sets be protected from the training pipeline's write access?