Re:A Guide to Synthesizing Adversarial Examples
by jwatte on Tuesday July 25, 2017 @09:32PM
(#14853164)
I have the feeling that the fact that imperceptible peturbations changes the labels, means that our networks/models don't yet look at the "right" parts of the input data.
Hopefully, this means research will focus on more robust classifiers based on weakness identified by adversarial approaches!
Hopefully, this means research will focus on more robust classifiers based on weakness identified by adversarial approaches!