Skip to main content

NOTICE: Due to a lapse in annual appropriations, most of this website is not being updated. Learn more.

Form submissions will still be accepted but will not receive responses at this time. Sections of this site for programs using non-appropriated funds (such as NVLAP) or those that are excepted from the shutdown (such as CHIPS and NVD) will continue to be updated.

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.

Proxy Validation and Verification for Critical AI Systems

Published

Author(s)

Phillip Laplante, Joanna DeFranco, D. Richard Kuhn, Jeff Voas

Abstract

This white paper offers a suggestion that prior testing artifacts from similar AI systems can be reused for new AI software. Testing AI and Machine learning software is difficult, and if prior testing results from similar systems could be applied as a proxy, this would be a significant research advance.
Citation
NIST Cybersecurity White Papers (CSWP) - 31
Report Number
31

Keywords

artificial intelligence, assurance, testing, verification

Citation

Laplante, P. , DeFranco, J. , Kuhn, D. and Voas, J. (2024), Proxy Validation and Verification for Critical AI Systems, NIST Cybersecurity White Papers (CSWP), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.CSWP.31, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=956743 (Accessed October 2, 2025)

Issues

If you have any questions about this publication or are having problems accessing it, please contact [email protected].

Created September 26, 2024
Was this page helpful?