UTC

AML.T0005.000

Replicate AI Model Behavior: Replicate Behavior from Gathered AI Artifacts

Adversaries may replicate AI model behavior by training or fine-tuning another model from gathered AI artifacts, such as representative datasets, published architectures, training objectives, documented hyperparameters, or pretrained components.

  • Tactic Resource Development
  • Tactic AI Attack Adaptation
  • Maturity: Demonstrated
  • Predictive AI
  • Generative AI
  • Agentic AI
Full entry on MITRE ATLAS →
Mitigations
  • Limit Public Release of InformationAML.M0000

    Limit the public release of technical information about the AI stack used in an organization's products or services. Technical knowledge of how AI is used can be leveraged by adversaries to perform targeting and tailor attacks to the target system.

    Policy

  • Limit Model Artifact ReleaseAML.M0001

    Limit public release of technical project details including data, algorithms, model architectures, and model checkpoints that are used in production, or that are representative of those used in production.

    Policy

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