Booth, H.
, Glasbrenner, J.
, Huang, H.
, Miniter, C.
and Sexton, J.
(2021),
Securing AI Testbed (Dioptra) Documentation, Dioptra Git Hub Project, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=932719, https://github.com/usnistgov/dioptra
(Accessed October 10, 2025)
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.
Securing AI Testbed (Dioptra) Documentation
Published
Author(s)
, James Glasbrenner, Howard Huang, Cory Miniter, Julian Sexton
Abstract
The NCCoE has built an experimentation testbed to begin to address the broader challenge of evaluation for attacks and defenses. The testbed aims to facilitate security evaluations of ML algorithms under a diverse set of conditions. To that end, it has a modular design enabling researchers to easily swap in alternative datasets, models, attacks, and defenses. The result is an ability to advance the metrology needed to ultimately help secure our ML-enabled systems. The Documentation includes user guidance for implementation, deployment, development, as well as tutorials and examples.Citation
Dioptra Git Hub Project
Pub Weblink
Pub Type
Websites
Download Paper
Keywords
Trustworthy AI, Artificial Intelligence, test bed, user guidance, implementation, deploy, user guide, metrics, robustness, resilience, AI security
Citation
Issues
If you have any questions about this publication or are having problems accessing it, please contact [email protected].
Created June 14, 2021, Updated November 29, 2022