AML-ATLAS-2026-15 | MITRE ATLAS Mapped 2026 – Top AI Threat Detection: Training Data Poisoning Pipeline Abuse (AML.T0020)

Ibrahim Saud@tektrix

•updated Sep 25, 2026•0•0•1

This rule detects potential AI model training data poisoning attempts by monitoring data pipeline audit logs for suspicious activities. Specifically, it flags bulk modifications to production training sets, ingestion from newly introduced external sources, or failures in data integrity checksums, which are indicative of attempts to influence or corrupt machine learning model training pipelines.