MITRE ATLAS 2026 Top AI Detection: Poisoned Model Publication to Public Model Hub (AML.T0058)

Ibrahim Saud@tektrix

•updated Sep 25, 2026•0•0•0

This rule monitors for potential exploitation of AI supply chain vulnerabilities, specifically targeting AML.T0058 (Publish Poisoned Models). It identifies the download of suspicious model artifact files (e.g., .pt, .pkl, .h5, .onnx) via common tools like curl, wget, or pip, and detects the subsequent insecure deserialization of these files using Python's pickle library when dangerous opcodes (REDUCE/GLOBAL) are combined with system command execution primitives (os.system, subprocess).