AML-ATLAS-2026-12 | MITRE ATLAS Mapped 2026 – Top AI Threat Detection: Erosion of AI Model Integrity (AML.T0031)
Detects sustained, statistically significant degradation in AI model performance (confidence and accuracy) and anomalous drift scores associated with specific callers or input sources. This behavior suggests a targeted attempt to erode model integrity through adversarial inputs rather than organic data drift.
Microsoft Sentinel (KQL)
