13 min listen
Adversarial AI
FromShort Wave
ratings:
Length:
10 minutes
Released:
Oct 24, 2019
Format:
Podcast episode
Description
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." Some of their experiments use seemingly simple techniques. Dina Temple-Raston has been looking into this for her special series, I'll Be Seeing You. Follow host Maddie Sofia on Twitter: @maddie_sofia. Or email the show at shortwave@npr.org.
Released:
Oct 24, 2019
Format:
Podcast episode
Titles in the series (100)
Seen Any Nazi Uranium? These Researchers Want To Know: Nazi Germany tried to build a nuclear reactor. How evidence of that effort was almost lost to history. by Short Wave