Science:Life Sciences
How Hackers Could Fool Artificial Intelligence
2020-09-21
Download
Right click and do "save link as"
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 shortwave@npr.org.
Learn more about sponsor message choices: podcastchoices.com/adchoices
NPR Privacy Policy
view more
For more, check out Dina's special series, I'll Be Seeing You.
Email the show at shortwave@npr.org.
Learn more about sponsor message choices: podcastchoices.com/adchoices
NPR Privacy Policy
More Episodes
Allergies Are Weird. So Are Cats
2023-04-05
2023-04-05
What we lose if the Great Salt Lake dries up
2023-03-21
2023-03-21
Venus And Earth: A Tale Of Two 'Twins'
2023-03-20
2023-03-20
Flying Into Snowstorms ... For Science!
2023-03-17
2023-03-17
It's Boom Times In Ancient DNA
2023-03-15
2023-03-15
The Race To Save A Tree Species
2023-03-08
2023-03-08
Get this podcast on your
phone, FREE
