AI engineering glossary · Evals guardrails AI security
What is jailbreak?
Jailbreak (also called jailbreaking): A prompt or technique that persuades a language model to ignore its safety training and produce content it is meant to refuse. Common forms include role-play, hypothetical framing and encoding tricks. Jailbreaks target the model's behaviour, whereas injection targets an application's instructions.
Jailbreak: an example
A user asks the model to act as a character with no rules and then requests instructions it would normally decline.
Related terms
More Evals guardrails AI security terms
- Judge calibration
- Least privilege
- Llama Guard
- LLM-as-a-judge
- lm-evaluation-harness
- Many-shot jailbreaking
- Membership inference attack
- Misinformation risk
Where you learn it
Jailbreak is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.