AI Glossary

Jailbreak

A prompt crafted to get a model to ignore its safety training and produce something it was trained to refuse.

See also

  • Prompt injection

    An attack in which input makes a model behave in ways its builders did not intend, either typed directly or hidden in content the model reads, such as a web page, an email or a document.

  • Red teaming

    Deliberately attacking an AI system the way an adversary would, to find harmful outputs, security holes or failures, before or after it is released.

Source: Wei, Haghtalab and Steinhardt, Jailbroken: How Does LLM Safety Training Fail? (2023) (opens in a new tab)

Cite this term.

CC BY 4.0, attribution required.

This term

Orbyt Labs, Jailbreak (AI Glossary), Oct 18, 2026. https://www.orbytlabs.ai/orbyt-collective/glossary/jailbreak

The dataset (JSON)

Orbyt Labs Glossaries (Oct 19, 2026), https://www.orbytlabs.ai/glossary#dataset

Last updated .