Log in or Sign up

NIST releases a tool for testing AI model risk

Discussion in 'Security in a World with AI' started by ronjor, Jul 28, 2024.

ronjor Global Moderator

Joined:

Jul 21, 2003

Posts:

177,020

Location:

Texas

Kyle Wiggers July 27, 2024

The National Institute of Standards and Technology (NIST), the U.S. Commerce Department agency that develops and tests tech for the U.S. government, companies and the broader public, has re-released a testbed designed to measure how malicious attacks — particularly attacks that “poison” AI model training data — might degrade the performance of an AI system.
Click to expand...

ronjor, Jul 28, 2024

#1

(You must log in or sign up to reply here.)

This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.

Accept Learn More...