1. This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies. Learn More.

Fooling The Machine

Discussion in 'AI in the News' started by RSS, Mar 31, 2016.

  1. RSS

    RSS New Member Member

    [​IMG]

    "We show you a photo that's clearly a photo of a school bus, and we make you think it's an ostrich," says Ian Goodfellow, a researcher at Google who has driven much of the work on adversarial examples. By altering the images fed into a deep neural network by just four percent, researchers were able to trick it into misclassifying the image with a success rate of 97 percent.

    Popular Science
    Link
    [​IMG]

    Continue reading...
     

Share This Page