Adversarial Examples Are a Natural Consequence of Test Error in Noise Adversarial Examples Are a Natural Consequence of Test Error in Noise
Paper summary Ford et al. show that the existence of adversarial examples can directly linked to test error on noise and other types of random corruption. Additionally, obtaining model robust against random corruptions is difficult, and even adversarially robust models might not be entirely robust against these corruptions. Furthermore, many “defenses” against adversarial examples show poor performance on random corruption – showing that some defenses do not result in robust models, but make attacking the model using gradient-based attacks more difficult (gradient masking). Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).
arxiv.org
scholar.google.com
Adversarial Examples Are a Natural Consequence of Test Error in Noise
Ford, Nic and Gilmer, Justin and Carlini, Nicholas and Cubuk, Ekin Dogus
arXiv e-Print archive - 2019 via Local Bibsonomy
Keywords: dblp


[link]
Summary by David Stutz 8 months ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and