News for hackers. Stuff that matters.

A comment on Attacking machine learning with adversarial examples. Parent comment

Re:Attacking machine learning with adversarial examples by emmab on Friday February 17, 2017 @05:58AM (#13667381)
> Except no amount of specially crafted noise will trick a human

Or quite possibly we just don't know how to construct the noise yet :P

[ Parent | on HN ]
Re:Attacking machine learning with adversarial examples by dkarapetyan on Friday February 17, 2017 @10:09AM (#13668686)
Well we do. Conspiracy theories are noise but not in the same category as pixel noise. When neural nets start falling for conspiracy theories then I'll start to worry about the coming singularity.
[ Parent | on HN ]