ML Anthology

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features'

Logan Engstrom, Justin Gilmer, Gabriel Goh, Dan Hendrycks, Andrew Ilyas, Aleksander Madry, Reiichiro Nakano, Preetum Nakkiran, Shibani Santurkar, Brandon Tran, Dimitris Tsipras, Eric Wallace
Distill 2019
doi:10.23915/distill.00019 /distill/2019/engstrom2019distill-discussion/

Abstract

Distill articles are interactive publications and do not include traditional abstracts. This summary was written for the ML Anthology. Hosts a structured discussion of the paper 'Adversarial Examples Are Not Bugs, They Are Features' by Ilyas et al., featuring six peer commentaries with new experiments and detailed author responses examining the role of non-robust features in neural networks.

Distill Code Semantic Scholar

Cite

Text

Engstrom et al. "A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features'." Distill, 2019. doi:10.23915/distill.00019

Markdown

[Engstrom et al. "A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features'." Distill, 2019.](https://mlanthology.org/distill/2019/engstrom2019distill-discussion/) doi:10.23915/distill.00019

BibTeX

@article{engstrom2019distill-discussion,
  title     = {{A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features'}},
  author    = {Engstrom, Logan and Gilmer, Justin and Goh, Gabriel and Hendrycks, Dan and Ilyas, Andrew and Madry, Aleksander and Nakano, Reiichiro and Nakkiran, Preetum and Santurkar, Shibani and Tran, Brandon and Tsipras, Dimitris and Wallace, Eric},
  journal   = {Distill},
  year      = {2019},
  doi       = {10.23915/distill.00019},
  url       = {https://mlanthology.org/distill/2019/engstrom2019distill-discussion/}
}