Countering Adversarial Images Using Input Transformations [pdf] (arxiv.org) 11 points by stablemap 8y ago ↗ HN
[–] rota219 8y ago ↗ 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. [–] stablemap 8y ago ↗ You might get an answer from Laurens at his post:https://www.facebook.com/lvdmaaten/posts/10156844136621038
[–] stablemap 8y ago ↗ You might get an answer from Laurens at his post:https://www.facebook.com/lvdmaaten/posts/10156844136621038
2 comments
[ 5.6 ms ] story [ 20.4 ms ] threadhttps://www.facebook.com/lvdmaaten/posts/10156844136621038