AIConfPaper
ICML 2019oral202 citations

Adversarial Examples Are a Natural Consequence of Test Error in Noise

Justin Gilmer, Nicolas Ford, Nicholas Carlini, Ekin Cubuk

Source ↗PDF ↗Scholar ↗TeX ↗

Abstract

Over the last few years, the phenomenon of

BibTeX
@InProceedings{pmlr-v97-gilmer19a,
  title = 	 {Adversarial Examples Are a Natural Consequence of Test Error in Noise},
  author =       {Gilmer, Justin and Ford, Nicolas and Carlini, Nicholas and Cubuk, Ekin},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {2280--2289},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/gilmer19a/gilmer19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/gilmer19a.html},
  abstract = 	 {Over the last few years, the phenomenon of
Adversarial Examples Are a Natural Consequence of Test Error in Noise · ICML 2019