NIST Warns of Cyberthreats to AI Models

Data-Poisoning Attacks Are Critical Threat to Machine Learning Security, NIST Warns
Machine learning systems continue are vulnerable to cyberattacks that could allow hackers to evade security and prompt data leaks, scientists at the National Institute of Standards and Technology warned. There is "no foolproof defense" against some of these attacks, researchers said.

ai models attacks continue critical cyberattacks cyberthreats data data leaks defense evade hackers leaks machine machine learning national nist poisoning poisoning attacks prompt researchers security standards systems technology threat vulnerable