News & Updates

This webinar presents a new project to develop NIST security control overlays for AI systems. These overlays adapt, tailor, and supplement the SP 800-53 controls to address AI-specific concerns, such as model integrity, data provenance, adversarial robustness, and transparency without reinventing the wheel.

NIST has released a concept paper and proposed action plan for developing a series of NIST SP 800-53 Control Overlays for Securing AI Systems, as well as a launching a Slack channel for this community of interest.

The National Cybersecurity Center of Excellence (NCCoE) has released the initial public draft of Internal Report (IR) 8579.  The comment period for this NIST IR closes on September 11, 2025.

NIST has published NIST AI 100-2e2025, Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations.

NIST Cybersecurity White Paper (CSWP) 31, Proxy Validation and Verification for Critical AI Systems: A Proxy Design Process has been published.

Today, NIST is releasing Special Publication (SP) 800-218A, Secure Software Development Practices for Generative AI and Dual-Use Foundation Models: An SSDF Community Profile.

NIST has posted an initial public draft of NIST Special Publication (SP) 800-218A, Secure Software Development Practices for Generative AI and Dual-Use Foundation Models: An SSDF Community Profile, for public comment. 

NIST has published a new report, NIST AI 100-2e2023, "Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations."

The initial public draft of NIST AI 100-2 (2003 edition), Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations, is now available for public comment.

The National Cybersecurity Center of Excellence (NCCoE) has released a new final project description, Mitigating AI/ML Bias in Context: Establishing Practices for Testing, Evaluation, Verification, and Validation of AI Systems.

A draft NIST Cybersecurity White Paper, Combination Frequency Differencing, is now available for public comment.

NIST has published NISTIR 8360, "Machine Learning for Access Control Policy Verification."

Draft NISTIR 8360, "Machine Learning for Access Control Policy Verification," is available for comment through May 7, 2021.

The NCCoE has released Draft NISTIR 8269, "A Taxonomy and Terminology of Adversarial Machine Learning," for public comment.  Comments are due by January 30, 2020.

NIST has release a draft white paper for public comment: "An Application of Combinatorial Methods for Explainability in Artificial Intelligence and Machine Learning." Comments are due by July 3, 2019.