UTC

AML.T0054

LLM Jailbreak

Adversaries may induce a large language model (LLM) to ignore, circumvent, or override its safety/alignment behaviors and/or guardrails to elicit outputs the model is intended to withhold. Once jailbroken, the LLM may be used in unintended ways by the adversary.

  • Tactic Privilege Escalation
  • Tactic Defense Evasion
  • Maturity: Realized
  • Generative AI
  • Agentic AI
Full entry on MITRE ATLAS →
Mitigations
  • Validate AI ModelAML.M0008

    Evaluate AI models against defined functional requirements before deployment and throughout their operational lifecycle. Validate newly trained or acquired models and repeat evaluation after fine-tuning, model updates, or changes to the conditions in which the model is used.

    Technical - AI

  • Generative AI GuardrailsAML.M0020

    Guardrails are safety controls placed between users, tools, and generative AI models to evaluate prompts, retrieved context, model outputs, and agent actions before they are accepted, executed, or shown to a user.

    Technical - AI

  • Generative AI GuidelinesAML.M0021

    Guidelines are instructions, policies, and behavioral constraints provided to a generative AI model to direct it toward desired outputs and away from unsafe, unreliable, or policy-violating behavior.

    Technical - AI

  • Generative AI Model AlignmentAML.M0022

    Generative AI Model Alignment is the process of training or fine-tuning a generative model to guide its output toward a set of human values, goals, or ethical principles.

    Technical - AI

  • AI Red TeamAML.M0035

    Establish an AI red team responsible for conducting recurring, authorized, and threat-informed red-teaming exercises to identify and remediate vulnerabilities in AI-enabled systems before deployment and throughout operation.

    Policy · Technical - AI · Technical - Cyber

From MITRE ATLAS 2026.10, Copyright 2021-2026 MITRE, Apache License 2.0.