U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Artificial intelligence

Search Publications

Search Title, Abstract, Conference, Citation, Keyword or Author
  • Published Date
Displaying 1 - 25 of 264

An Improved Robotic Workcell for Operational Technology (OT) Research

December 18, 2025
Author(s)
Timothy Zimmerman, Michael Pease, Michael Dawson
The National Institute of Standards and Technology (NIST) has constructed a discrete manufacturing workcell to support its operational technology (OT) and critical infrastructure research. This work is an improvement on the "Collaborative Robotics Testbed"

Robust AI Security and Alignment: A Sisyphean Endeavor?

December 12, 2025
Author(s)
Apostol Vassilev
This manuscript establishes information-theoretic limitations for robustness of AI security and alignment by extending Gödel's incompleteness theorem to AI. Knowing these limitations and preparing for the challenges they bring is critically important for

2025 NIST GenAI Text Challenge Evaluation Plan

September 18, 2025
Author(s)
Seungmin Seo, Hariharan Iyer, Yooyoung Lee
The NIST Generative AI (GenAI) Text Challenge is an evaluation program designed to probe the capabilities and limitations of generative AI models from three complementary perspectives: Generator, Prompter, and Discriminator. The challenge will focus on two

EVALUATING IDENTITY LEAKAGE IN SPEAKER DE-IDENTIFICATION SYSTEMS

August 21, 2025
Author(s)
Seungmin Seo, Oleg Aulov, Afzal Godil, Kevin Mangold
Speaker de-identification aims to conceal a speaker's identity while preserving intelligibility of the underlying speech. We introduce a benchmark that quantifies residual identity leak- age with three complementary error rates: equal error rate (EER)

From Traditional Topic Models to LLM Topic Models: Can Large Language Models Replace Traditional Topic Models?

August 1, 2025
Author(s)
Zongxia Li, Lorena Calvo Bartolome, Alexander Hoyle, Daniel Stephens, Paiheng Xu, Alden Dima, Jordan Boyd-Graber, Juan Fung
A common use of NLP is to facilitate the understanding of large document collections, with models based on Large Language Models (LLMs) replacing probabilistic topic models. Yet the effectiveness of LLM-based approaches in real-world applications remains

Quasi-Deterministic Channel Propagation Model for Human Sensing: Gesture Recognition Use Case

July 9, 2025
Author(s)
Jack Chuang, Raied Caromi, Jelena Senic, Samuel Berweger, Neeraj Varshney, Jian Wang, Anuraag Bodi, Camillo Gentile, Nada Golmie
We describe a quasi-determinstic channel propagation model for human gesture recognition reduced from real-time measurements with our context aware channel sounder, considering four human subjects and 20 distinct body motions, for a total of 120,000

2024 NIST GenAI (Pilot Study): Text-to-Text Evaluation Overview and Results

June 25, 2025
Author(s)
Hariharan Iyer, Seungmin Seo, Lukas Diduch, Kay Peterson, George Awad, Yooyoung Lee
The 2024 NIST Generative AI (GenAI) Pilot Study focuses on evaluating text-to-text (T2T) generation and discrimination tasks to assess the capabilities and limitations of generative AI models and AI detectors. The study aims to measure the effectiveness of

Hallucination Detection in Large Language Models Using Diversion Decoding

June 24, 2025
Author(s)
Basel Abdeen, S M Tahmid Siddiqui, Meah Tahmeed Ahmed, Anoop Singhal, Latifur Khan, Punya Modi, Ehab Al-Shaer
Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advanced text generation capabilities, LLMs exhibit hallucination tendencies, where they generate factually

NIST GenAI (Pilot): an Overview of Text-to-Text Evaluation Results

May 5, 2025
Author(s)
Yooyoung Lee, Hariharan Iyer
The 2024 NIST Generative AI (GenAI) Pilot Study focuses on evaluating text-to-text (T2T) generation and discrimination tasks to assess the capabilities and limitations of generative AI models. The study aims to measure the effectiveness of AI-generated

A Plan for Global Engagement on AI Standards

April 29, 2025
Author(s)
Jesse Dunietz, Mark Latonero, Kathleen Roberts
This plan has been developed by the Department of Commerce in coordination with the Department of State and agencies across the U.S. Government. It reflects more than 65 comments received in response to a December 2023 Request for Information

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

March 24, 2025
Author(s)
Apostol Vassilev, Alina Oprea, Alie Fordyce, Hyrum Anderson, Xander Davies, Maia Hamin
This NIST Trustworthy and Responsible AI 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

Detection limits of AI-based SEM dimensional metrology

March 14, 2025
Author(s)
Peter Bajcsy, Brycie Wiseman, Michael Paul Majurski, Andras Vladar
The speed of in-line scanning electron microscope (SEM) measurements of linewidth, contact hole, and overlay is critically important for identifying the measurement area and generating indispensable process control information. Sample charging and damage

Semantics for Enhancing Communications- and Edge-Intelligence-enabled Smart Sensors: A Practical Use Case in Federated Automotive Diagnostics

March 10, 2025
Author(s)
Eugene Song, Thomas Roth, David A. Wollman, Eoin Jordan, Martin Serrano, Amelie Gyrard
Modern edge artificial intelligence (AI) chipsets and edge-intelligence-enabled smart sensors frameworks support real-time data processing and event detection at the signal source. Beyond just measuring local conditions and transmitting corresponding

NIST Open Media Forensics Challenge (OpenMFC Briefing for IIRD)

January 27, 2025
Author(s)
Haiying Guan
The rapid advancement of artificial intelligence (AI) has led to the emergence of several technologies, including Generative Adversarial Networks (GANs), deepfakes, generative AI, CGI, and anti-forensics techniques. These technologies pose a significant

Reflection of its Creators: Qualitative Analysis of General Public and Expert Perceptions of Artificial Intelligence

October 16, 2024
Author(s)
Theodore Jensen, Mary Frances Theofanos, Kristen K. Greene, Olivia Williams, Kurtis Goad, Janet Bih Fofang
The increasing prevalence of artificial intelligence (AI) will likely lead to new interactions and impacts for the general public. An understanding of people's perceptions of AI can be leveraged to design and deploy AI systems toward human needs and values
Was this page helpful?