How Hackers Could Fool Artificial Intelligence

How Hackers Could Fool Artificial Intelligence

  • By
  • Episode
      245
  • Published
      Sep 21, 2020
  • Publisher
0 Ratings
0
Episode
245 of 1389
Duration
12min
Language
English
Format
Category
Non-fiction

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


Listen and read

Step into an infinite world of stories

  • Read and listen as much as you want
  • Over 1 million titles
  • Exclusive titles + Storytel Originals
  • 7 days free trial, then €9.99/month
  • Easy to cancel anytime
Details page - Device banner - 894x1036
Cover for How Hackers Could Fool Artificial Intelligence

Other podcasts you might like ...