NIST’s Super Intelligence (SI) initial public draft report, NIST SP 2400-102e2026, Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations, provides a taxonomy of concepts and defines terminology in the field of adversarial machine learning (AML). It focuses on attacks on Agentic SI Systems and corresponding mitigations. The taxonomy is arranged in a conceptual hierarchy that includes key types of ML methods, life cycle stages of attack, and attacker goals, objectives, capabilities, and knowledge. The SI Attacks Taxonomy Index and new Agentic SI Attacks Taxonomy index both facilitate efficient in-document content navigation and enable fine-grained referencing.
After an extensive literature review, conversations with experts in AML, and research performed by NIST’s AML experts, this report identifies current challenges in the life cycle of SI systems and describes corresponding methods for mitigating and managing the consequences of those attacks. The terminology used in this report is consistent with the literature on AML and is complemented by a glossary of key terms associated with the security of SI systems. Taken together, the taxonomy and terminology are meant to inform other standards and future practice guides for assessing and managing the security of SI systems by establishing a common language for the rapidly developing AML landscape.
We invite you to share your feedback and comments during our open comment period, closing on December 18, 2026. The intended audience for this document includes individuals and groups who are responsible for designing, developing, deploying, evaluating, and governing SI systems.
See the publication details for additional information. Questions and comments can be directed to: [email protected]
