UTC

AML.T0120

AI Artifact Repository

Adversaries may repurpose AI artifact repositories as asynchronous command-and-control channels. Commands, payloads, or tasking may be placed in repository objects for a compromised system to retrieve or poll. The compromised system may then write execution results, status, or collected information back to the repository for retrieval by the adversary.

  • Tactic Command and Control
  • 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

  • AI Telemetry Logging and MonitoringAML.M0024

    Implement logging and monitoring across the AI lifecycle to detect suspicious activity and support investigation. Capture security-relevant access, changes, and operations across data pipelines, model development, deployment, and connected systems.

    Technical - Cyber

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