We use cookies to understand how you use our platform and to improve your experience. Click “Accept All” to consent, or “Decline non-essential” to opt out of non-essential cookies. Read our Privacy Policy.
Assessing AI Model Security From the Outside In | Matt Fredrikson
Sep 22, 2026 · 37 min · 11 segments
The security and reliability of the code in AI models is a huge question mark, because the models are black boxes that aren't accessible to outsiders. Matt Fredrikson, professor at Carnegie Mellon…
The security and reliability of the code in AI models is a huge question mark, because the models are black boxes that aren'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.
The security and reliability of the code in AI models is a huge question mark, because the models are black boxes that aren't accessible to outsiders. Matt Fredrikson, professor at Carnegie Mellon…
Matt FredriksonGuest
Dennis FisherHost