AML-ATLAS-2026-14 | MITRE ATLAS Mapped 2026 – Top AI Threat Detection: AI Model Weight Poisoning (AML.T0018.000)
Detects unauthorized or unreviewed modifications to AI model weights, retraining jobs, or pushes to the model registry within MLOps pipelines. This activity is monitored to prevent AI model weight poisoning, ensuring that all model-related changes undergo required peer-review or approval processes before deployment.
Microsoft Sentinel (KQL)
