NIST Adversarial ML: Public Draft for comments-Taxonomy/terms for attacks

NIST published the public draft of Special Publication 2400-102e2026, "Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations," on November 9, 2026, with comments open through December 18, 2026. The draft, authored by Apostol Vassilev and Maia Hamin of NIST alongside Alina Oprea (Northeastern University), Alie Fordyce (ElevenLabs) and Xander Davies (U.K. AI Security Institute), focuses on attacks against Agentic SI Systems and corresponding mitigations in Section 4, and adds a new Agentic SI Attacks Taxonomy index. NIST is seeking comment on the latest attacks threatening SI systems, effective mitigations, and terminology that needs standardization, with the taxonomy intended to inform other standards and future practice guides.

Date Published: November 9, 2026 Comments Due: Email Comments to: Author s Apostol Vassilev NIST , Alina Oprea Northeastern University , Alie Fordyce ElevenLabs , Xander Davies U.K. AI Security Institute , Maia Hamin NIST Announcement The public draft of NIST Special Publication 2400-102e2026, Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations, is now available for comments. This edition builds on the historical NIST AI 100-2 series https://csrc.nist.gov/publications/search?sortBy-lg=relevance&viewMode-lg=brief&ipp-lg=50&status-lg=Final%2CDraft&series-lg=AI . This NIST Special Publication on Super Intelligence SI establishes a taxonomy of attacks and mitigations and defines terminology in the field of adversarial machine learning AML . 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 understanding the rapidly developing AML landscape. The focus of this edition is on the attacks on Agentic SI Systems and corresponding mitigations - see Section 4 of the report. The SI Attacks Taxonomy Index is updated as well with the new Agentic SI Attacks Taxonomy index, to facilitate efficient content navigation within the document and enable fine-grain referencing. NIST is specifically interested in comments on and recommendations for the following topics: - What are the latest attacks that threaten the existing landscape of SI systems and in particular Agentic SI Systems? - What are the latest effective mitigations to counter these attacks? - Is there new terminology that needs standardization? The public comment period for this draft is open through December 18, 2026 . This NIST Special Publication 2400 report provides a taxonomy of concepts and defines terminology in the field of adversarial machine learning AML . 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. This report also 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. This NIST Special Publication 2400 report provides a taxonomy of concepts and defines terminology in the field of adversarial machine learning AML . The taxonomy is arranged in a conceptual hierarchy that includes key types of ML methods, life cycle stages of attack, and attacker goals, objectives,... See full abstract pubs-abstract-header This NIST Special Publication 2400 report provides a taxonomy of concepts and defines terminology in the field of adversarial machine learning AML . 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. This report also 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. Hide full abstract pubs-abstract-header Keywords artificial intelligence; machine learning; attack taxonomy; abuse; data poisoning; evasion; privacy breach; attack mitigation; large language model; chatbot Control Families None selected