But these technologies are also vulnerable to another kind of weakness known as “adversarial examples.” An adversarial example occurs when a neural net identifies an image as one thing–while any person looking at it sees something else. The phenomenon was discovered in 2013, when a group of ...
from Google Alert - vulnerability http://ift.tt/2BvLqHE
via IFTTT
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment