MITRE ATLAS · Resource Development
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.
Mitigations
- Sanitize Training Data
- Vulnerability Scanning
- Threat Intelligence Program
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.