NIST has published a draft report titled Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations. The document provides a conceptual hierarchy for attacks on Agentic SI Systems and defines related terminology. It aims to establish a common language for assessing and managing the security of these systems. The public comment period for the draft closes on December 18, 2026.
Read the full story at csrc.nist.gov.
