Skip to main content
11 events
when toggle format what by license comment
Mar 14, 2020 at 13:59 history closed nbro Duplicate of Is artificial intelligence vulnerable to hacking? [closed]
Oct 12, 2019 at 20:19 comment added quester YES even noise added can fool any classifier - some may be trained on noised examples but you can always find a way although it's a bit hacking unknown algorithm so I would compare it to birthday technique
Oct 11, 2019 at 22:50 review Close votes
Oct 12, 2019 at 22:23
Oct 11, 2019 at 22:20 history edited nbro CC BY-SA 4.0
I reformulated the question to hopefully make it clearer.
Oct 24, 2018 at 22:44 comment added k.c. sayz 'k.c sayz' Perhaps what you are looking for is the notion of adversarial attacks on machine learning systems?
Oct 24, 2018 at 20:02 history edited DukeZhou
edited tags
Oct 24, 2018 at 20:01 comment added DukeZhou You may appreciate this story about someone hacking an AI for revenge: Unchained: A story of love, loss, and blockchain (MIT Tech Review)
Oct 24, 2018 at 14:42 answer added Jordan Benge timeline score: 5
Oct 24, 2018 at 14:41 answer added GIA timeline score: 1
Oct 24, 2018 at 13:05 review Close votes
Oct 24, 2018 at 20:03
Oct 24, 2018 at 7:21 history asked ME. CC BY-SA 4.0