One pixel attack for fooling deep neural networks. https://boingboing.net/2017/10/31/classifiers-are-fragile.html …pic.twitter.com/jraaggrspS
11:53 AM - 31 Oct 2017
0 replies
2 retweets
2 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.