UTC

AML.T0115.000

Publish Poisoned AI Artifacts: Datasets

Adversaries may publish poisoned datasets intended for training or fine-tuning AI models. The dataset may be newly created or a modified variant of a legitimate dataset and may contain manipulated samples, labels, annotations, or metadata.

  • Tactic Resource Development
  • Maturity: Demonstrated
  • Predictive AI
  • Generative AI
  • Agentic AI
Full entry on MITRE ATLAS →
Mitigations
  • Sanitize Training DataAML.M0007

    Detect, quarantine, and remove or remediate poisoned data before it is used to train an AI model. Apply screening when datasets are acquired or updated, and before new data is incorporated into active learning workflows.

    Technical - AI

  • Threat Intelligence ProgramAML.M0042

    A Threat Intelligence Program enables organizations to proactively collect, analyze, and share information on threats to AI and cyber systems by leveraging internal observations and external reporting.

    Policy

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