RS Glossary
Jailbreak
A jailbreak is a technique or prompt pattern intended to bypass an AI system's behavioral restrictions and elicit content or actions the system is designed to refuse.
- Review state
- Needs review
- Freshness
- Current
- Version
- 2
- Jailbreak
- AI Jailbreak
Remember it this wayA jailbreak tries to talk past the guardrail.
In plain language
The requester reframes, disguises, decomposes, or encodes a disallowed request in hopes that the model will follow it despite its safeguards.
Why it matters
Jailbreak testing can reveal weaknesses, but public success claims may be narrow, temporary, or dependent on a particular model version and setup.
Example
A user wraps a prohibited request in elaborate role-play and indirect instructions to try to evade the assistant's refusal behavior.
Common misconception
Jailbreak is not identical to prompt injection. Jailbreaks usually target behavioral restrictions directly; prompt injection often exploits instructions embedded in content or application workflows.
Related terms
Sources
- NIST, *Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations* (NIST AI 100-2 E2025)authoritative security taxonomy and glossary covering jailbreak attacks and related prompt-based attacks.
Learn more
- Evaluate bypass attempts through authorized [[red-teaming|Red Teaming]].
Public history
39 recorded events · 39 public summaries
A potential shared concept was discussed and selected for initial glossary drafting.
The captured candidate received a complete initial draft and entered section-level human review.
Radar reviewed the initial definition draft for human consideration.
Radar reviewed the initial plain-language-explanation draft for human consideration.
Radar reviewed the initial why-it-matters draft for human consideration.
Radar reviewed the initial example draft for human consideration.
Radar reviewed the initial common-misconception draft for human consideration.
Radar reviewed the initial remember-it-this-way draft for human consideration.
Radar reviewed the initial related-terms draft for human consideration.
Radar reviewed the initial sources draft for human consideration.
Radar reviewed the initial learn-more draft for human consideration.
A proposal was opened for section-level human review while preserving the current version.
A human reviewer opened a proposed revision while preserving the current approved or captured version.
definition returned for revision.
plain-language-explanation approved by a human reviewer.
why-it-matters approved by a human reviewer.
example approved by a human reviewer.
common-misconception approved by a human reviewer.
remember-it-this-way approved by a human reviewer.
related-terms approved by a human reviewer.
sources approved by a human reviewer.
Radar issue jailbreak-authoritative-source was accepted-as-is by the human section decision.
learn-more approved by a human reviewer.
The unchanged definition is approved; the reviewer instruction was explicitly about internet sources and was routed to Sources.
Sources returned for authoritative internet-source replacement, matching the reviewer instruction attached to Definition.
Requested wording was prepared without changing approved or existing sections.
Radar reviewed the pending sources section for human consideration.
Radar must rereview the complete jailbreak term after an accepted text change.
Radar must rereview the complete jailbreak term after an accepted text change.
Radar must rereview the complete jailbreak term after an accepted text change.
Radar must rereview the complete jailbreak term after an accepted text change.
Radar must rereview the complete jailbreak term after an accepted text change.
Radar must rereview the complete jailbreak term after an accepted text change.
Radar must rereview the complete jailbreak term after an accepted text change.
Radar must rereview the complete jailbreak term after an accepted text change.
Radar must rereview the complete jailbreak term after an accepted text change.
sources approved by a human reviewer.
sources approved wording became the current section text.
All section gates are approved; content version 2 is now a fully approved term.
Source: vault/Glossary/terms/jailbreak/term.md · sha256:f0f8567faf3c6dc43836a5afd6377b67345fa84f0c99ac1e937531a0f0db52cf · Release: rs-glossary-glossary-team-poc-0.5.5-2026-09-02