Jailbreak
An adversarial input that bypasses a model's safety training to produce prohibited output. Common patterns: role-play framing ("pretend you are..."), hypothetical framing ("in a fiction..."), and multi-turn escalation. Related to but distinct from prompt injection.
Related terms
- Prompt Injection
An attack where adversarial instructions embedded in untrusted content (user input, retrieved documents, tool responses) hijack the model into ignoring its original instructions. Considered the primary security risk for LLM applications; defenses include separation of channels and output validation.
- Red-Teaming
Structured adversarial testing of an AI system, either manually or via automated attack pipelines, to find prompt injection, jailbreak, harmful-output, and misuse vulnerabilities before release. Increasingly required by AI regulation for high-risk systems.
Related on this site
Where this fits
Jailbreak is part of the Evaluation & Governance vocabulary used in the Generative AI Maturity Framework. See the full glossary for the complete set of 149 defined terms, or take the free maturity assessment to see where your organisation stands.