AML.T0115
Publish Poisoned AI Artifacts
Adversaries may create or modify AI artifacts and publish them through public or shared distribution channels to facilitate compromise of downstream AI systems. Poisoned AI artifacts may include datasets, models, and AI agent tools containing malicious content, behaviors, code, or configurations.
- Tactic Resource Development
- Maturity: Realized
- Predictive AI
- Generative AI
- Agentic AI
- 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
- Vulnerability ScanningAML.M0016
Vulnerability scanning is used to find potentially exploitable software vulnerabilities to remediate them.
Technical - Cyber
- 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.