UTC

AML.T0044

Full AI Model Access

This means the adversary has complete knowledge of the model architecture, its parameters, and class ontology. They may exfiltrate the model to Craft Adversarial Data and Verify Attack in an offline environment where it is hard to detect their behavior.

  • Tactic AI Model Access
  • Maturity: Demonstrated
  • Predictive AI
  • Generative AI
  • Agentic AI
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

  • 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.