Re:Countering Adversarial Images Using Input Transformations...
by rota219 on Friday November 03, 2017 @11:45AM
(#15620031)
How does your work compare to https://openreview.net/pdf?id=S18Su--CW, it seems you only evaluate your model against non-iterative adversaries rather than iterative and stronger ones like PGD.
[ Parent
| on HN ]