“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 490 retweets 650 likes -
Replying to @Meaningness
I looked for, but couldn't find, a lazy way to run code to generate those patterns (e.g.Matlab, Jupyter). Do you have one?
1 reply 0 retweets 0 likes -
Replying to @tuck1s
No… you could contact the authors of the paper I guess?
1 reply 0 retweets 0 likes -
Replying to @Meaningness
Have done. My motivation is purely as a playful ML amateur. Curiously, perturbations look a bit like artefacts inhttps://goo.gl/mMRjaD
1 reply 0 retweets 0 likes
Replying to @tuck1s
Yes; which makes sense, because those are specifically the things the net is looking for. Add them and it gets confused.
9:01 AM - 31 Mar 2017
0 replies
0 retweets
1 like
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.