Assessing AI Model Security From the Outside In | Matt Fredrikson

<p>The security and reliability of the code in AI models is a huge question mark, because the models are black boxes that aren&#39;t accessible to outsiders. Matt Fredrikson, professor at Carnegie Mellon University and founder of Gray Swan AI, joins Dennis to talk about the challenge of assessing these models and how a community of red teamers is trying to meet it.</p>