Top AI 2026 | MITRE ATLAS Mapped AML.T0044 – Unauthorized White-Box Model Artifact Exfiltration (AML-DET-012)
Detects anomalous, unauthorized access to machine learning model artifacts (e.g., .onnx, .pt, .h5) within object storage or model registries. The rule identifies suspicious patterns including high-volume file reads by non-ML team identities, lack of multi-factor authentication, or access from geolocations outside approved operating regions, indicative of potential model exfiltration or intellectual property theft.
YARA-L

