13 May 2019
AI can easily be tricked into saying a picture of a cat is a dogJohn Lund/GettyBy Linda GeddesWhy did the machine think the turtle was a rifle? No, this isn’t a bad joke, but one of many recent examples of machines being tricked into seeing or hearing things that aren’t there.
Artificial intelligence is easily confused by so-called adversarial examples and like many others, Aleksander Madry at the Massachusetts Institute of Technology had thought they were bugs that would disappear with better algorithms or ways to train them.
But he and his colleagues have now …
Quarterly by Direct DebitInclusive of applicable taxes (VAT)Existing subscribers, please log in with your email address to link your account access.