ZARZA We are Zarza, the prestigious firm behind major projects in information technology.
Listen "How Hackers Could Fool Artificial Intelligence"
Episode Synopsis
Artificial intelligence might not be as smart as we think. University and military researchers are studying how attackers could hack into AI systems by exploiting how these systems learn. It's known as "adversarial AI." In this encore episode, Dina Temple-Raston tells us that some of these experiments use seemingly simple techniques. For more, check out Dina's special series, I'll Be Seeing You. Email the show at [email protected] more about sponsor message choices: podcastchoices.com/adchoicesNPR Privacy Policy
More episodes of the podcast Short Wave
Hot galaxies alert!
09/01/2026
Micro forests: an emerging climate hero?
07/01/2026
Did Earth’s Water Come From Space?
05/01/2026
The trouble of zero
02/01/2026
Climate Anxiety Is Altering Family Planning
30/12/2025
Why Drones Are Catching Whale Breaths
26/12/2025
In God we trust