“Universal adversarial perturbations” seems most dramatic ML result in years; if so, not getting deserved attention https://arxiv.org/pdf/1610.08401v1.pdf …
-
-
Replying to @Meaningness
Result: there is a *fixed*, human-invisible map you can add to *any* image, and it renders it unclassifiable by multiple DL systemspic.twitter.com/s4zMsPy6Jy
22 replies 502 retweets 655 likes -
Replying to @Meaningness
I think the perturbations are specific to individual networks?
2 replies 0 retweets 2 likes -
Replying to @St_Rev @Meaningness
That's something they test. Somewhat specific, nonspecific enough to be interesting.
1 reply 0 retweets 0 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.
. Banned in Sweden. SubGenius, Zhuangist, white-hat troll. Defrocked mathematician. Brain problems.