How Hackers Could Fool Artificial Intelligence

Short Wave
|

Automatic TRANSCRIPT

Hey everybody, matty Safai here. Today we've got one for you that we first published last year when shortwave was just two weeks old barely lift in our little baby podcasts head up on our own for the first time. Episodes. All about how artificial intelligence works and how it can be hacked plus disco music. We're back tomorrow with a new episode and don't forget to subscribe to or follow shortwave wherever you get your podcasts. You're listening to shortwave. From NPR. Hey everybody matty Safai here again, this time with NPR special correspondent Dina Temple Ralston Hayden Hey there. So you're here because you've been doing some really cool reporting about artificial intelligence as part of your special series I'll be seeing you yet. We we did a story that it was explaining how works and how it's finding its way into everything from refrigerators to insurance even conservation but you also found out that for all of its potential there are some real concerns about hacking into Ai. There's actually a whole field of study that is focused on this. It's called adversarial or evil. evil. It's a big enough concern that Darpa. The military's research arm has created this whole program to study it, and it's called guaranteeing a robustness against deception or luckily it has a short dame guard. The government is so good at naming things to do you know it is quite the name. So are really good at creating tongue twisters. Basically what they're trying to do is imagine adversaries hacking into systems, and as they see, it affect everything from my public opinion to driverless cars. So it has huge implications.

Coming up next