Imaginary numbers help AIs solve the very real problem of adversarial imagery • The Register
Boffins from Duke University say they have figured out a way to help protect artificial intelligences from adversarial image-modification attacks: by throwing a few imaginary numbers their way. […] The problem with reliability: adversarial attacks which modify the input imagery in a way imperceptible to the human eye. In an example from a 2015 paper Read more about Imaginary numbers help AIs solve the very real problem of adversarial imagery • The Register[…]