UTC

AML.T0011.000

User Execution: Unsafe AI Artifacts

Adversaries may develop new AI artifacts or manipulate existing AI artifacts that have a deleterious effect when loaded, executed, interpreted, or used for inference by a victim. The unsafe artifacts may continue to work as expected from the victim's perspective.

  • Tactic Execution
  • Maturity: Realized
  • Predictive AI
  • Generative AI
  • Agentic AI
  • Enterprise
Full entry on MITRE ATLAS →
Mitigations
  • Restrict Library LoadingAML.M0011

    Prevent abuse of library loading mechanisms in the operating system and software to load untrusted code by configuring appropriate library loading mechanisms and investigating potential vulnerable software.

    Technical - Cyber

  • Code SigningAML.M0013

    Enforce binary and application integrity with digital signature verification to prevent untrusted code from executing. Adversaries can embed malicious code in AI software or models. Developers should also cryptographically sign SBOM and AIBOM components that track model or data provenance.

    Technical - Cyber

  • Verify AI ArtifactsAML.M0014

    Verify the integrity and authenticity of AI artifacts before importing, loading, or deploying them. Artifacts may include model weights and checkpoints, datasets, tokenizers, model configurations, prompt templates, and agent configuration files.

    Technical - Cyber

  • Vulnerability ScanningAML.M0016

    Vulnerability scanning is used to find potentially exploitable software vulnerabilities to remediate them.

    Technical - Cyber

  • User TrainingAML.M0018

    Educate AI model developers to on AI supply chain risks and potentially malicious AI artifacts. Educate users on how to identify deepfakes and phishing attempts.

    Policy

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