CT-GENAI Question 35

Community Discussion

Written by other learners. Comments can disagree with the marked answer — check the official documentation when in doubt.

• Chose B0

  - A jailbreak is a prompt designed to bypass an LLM's safety training so the model produces content it normally would refuse. Famous examples include 'DAN' (Do Anything Now), encoded payload tricks, and roleplay-based jailbreaks. Server-level attacks, DDoS, and SQL injection are unrelated traditional security vulnerabilities.