Data leaks
A section of the "Security" topic. The questions check an understanding of practice, not memory of specific library APIs. After each answer comes a review: why the correct option is right, what is wrong with each incorrect one and which chapter to read.
Quiz difficulty Formats: several correct options, one correct option
01
What we check
- Where the model learns too much
- Personal data in training
- How to keep personal data out of training data
- A PII filter on the output
- Leaking others' documents through RAG
- Lessons from the Scatter Lab case
02
Where to read
- Li, AI Agents in Depthsec. 3.3.3
- Wilson, The Developer's Playbook for LLM Securitych. 5 · ch. 7