UTC

AML.T0048.004

External Harms: AI Intellectual Property Theft

Adversaries may appropriate AI-related intellectual property in a manner that causes economic or competitive harm to the victim organization. Targeted material may include model architectures and weights, training data, or model behaviors and capabilities.

  • Tactic Impact
  • Maturity: Realized
  • Predictive AI
  • Generative AI
  • Agentic AI
  • Enterprise
Full entry on MITRE ATLAS →
Mitigations
  • Control Access to AI Models and Data at RestAML.M0005

    Establish access controls on internal model registries and limit internal access to production models. Limit access to training data only to approved users.

    Policy

  • Encrypt Sensitive InformationAML.M0012

    Encrypt sensitive data such as AI models to protect against adversaries attempting to access sensitive data.

    Technical - Cyber

  • AI Model Distribution MethodsAML.M0017

    Deploying AI models to edge devices can increase the attack surface of the system. Consider serving models in the cloud to reduce the level of access the adversary has to the model. Also consider computing features in the cloud to prevent gray-box attacks, where an adversary has access to the model preprocessing methods.

    Policy

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