NIST · March 24, 2025

Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations

Why it matters

NIST finalizes AI 100-2e2025, providing a terminology and taxonomy for adversarial machine learning across predictive and generative AI systems.

My takeaway: Use NIST’s vocabulary as a shared threat-modeling language. Map each system component to applicable attack stages and adversary capabilities, select mitigations that can be tested, and turn the resulting scenarios into evaluation cases and monitoring requirements.