Inside AI Policy

April 12, 2024

NIST security researcher offers taxonomy for mitigating AI privacy threats

By Rick Weber / March 19, 2024

A leading cybersecurity scientist at the National Institute of Standards and Technology is offering a taxonomy for assessing artificial intelligence risks and adversarial machine learning that pose unique threats to privacy and data security, while recommending the use of a mathematical framework referred to as “differential privacy” to enable data sharing with privacy protections.

“The data-driven approach of [machine learning] introduces additional security and privacy challenges in different phases of ML operations besides the classical security and privacy threats faced...

Log in to access this content.

Not a subscriber? Sign up for 30 days free access to exclusive news and analysis on artificial intelligence regulations and more.