{
 "id": "https://redfinchadvisory.com/lexicon/jailbreak",
 "slug": "jailbreak",
 "prefLabel": "Jailbreak",
 "altLabel": [],
 "hiddenLabel": [],
 "definition": "A type of AI system attack which attempts to 'convince' a system to ignore its rules, guardrails, or system instructions.",
 "scopeNote": "There are levels of guardrails that can defend against an attack of this sort, but the viability of these attacks is why deterministic guardrails should also be in place.",
 "tier": null,
 "group": "Risks",
 "broader": [
  "https://redfinchadvisory.com/lexicon/ai-security"
 ],
 "narrower": [],
 "related": [
  {
   "id": "https://redfinchadvisory.com/lexicon/prompt-injection",
   "type": "confused"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/deterministic-guardrail",
   "type": "related"
  }
 ],
 "links": [],
 "modified": "2026-10-20",
 "markdown": "https://redfinchadvisory.com/lexicon/jailbreak.md",
 "inScheme": {
  "id": "https://redfinchadvisory.com/lexicon",
  "version": "1.0",
  "currentAsOf": "2026-10-21"
 }
}