AIConfPaper
ICML 2022oral79 citations

Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them

Florian Tramer

Source ↗PDF ↗Scholar ↗

Abstract

Making classifiers robust to adversarial examples is challenging. Thus, many works tackle the seemingly easier task of

BibTeX
@InProceedings{pmlr-v162-tramer22a,
  title = 	 {Detecting Adversarial Examples Is ({N}early) As Hard As Classifying Them},
  author =       {Tramer, Florian},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {21692--21702},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/tramer22a/tramer22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/tramer22a.html},
  abstract = 	 {Making classifiers robust to adversarial examples is challenging. Thus, many works tackle the seemingly easier task of
Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them · ICML 2022