ARTIFICIAL INTELLIGENCE: How to Fool AI Into Seeing Something That Isn't There Cade Metz | WIRED "Today, neural nets are quite good at recognizing faces and spoken words...but they do make mistakes...You can subtly alter an image so that a neural network will think it includes something it doesn't...Imagine a face recognition system that uses a neural network to control access to a top-secret facility. You could fool it into thinking you're someone who you're not."...
This Week's Awesome Stories From Around the Web (Through July 30th)
Singularity Hub - 30 Jul 2016 19:00
ARTIFICIAL INTELLIGENCE: How to Fool AI Into Seeing Something That Isn't There Cade Metz | WIRED "Today, neural nets are quite good at recognizing faces and spoken words...but they do make mistakes...You can subtly alter an image so that a neural network will think it includes something it doesn't...Imagine a face recognition system that uses a neural network to control access to a top-secret facility. You could fool it into thinking you're someone who you're not."...
Share this Article
Recommended