Competition on robust deep learning

This perspective paper proposes a new adversarial training method based on large-scale pre-trained models to achieve state-of-the-art adversarial robustness on ImageNet.

Detalles Bibliográficos
Autores principales: Dong, Yinpeng, Liu, Chang, Xiang, Wenzhao, Su, Hang, Zhu, Jun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2023
Materias:
PERSPECTIVE
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10257479/
https://www.ncbi.nlm.nih.gov/pubmed/37304460
http://dx.doi.org/10.1093/nsr/nwad087
_version_ 1785057310965497856
author Dong, Yinpeng
Liu, Chang
Xiang, Wenzhao
Su, Hang
Zhu, Jun
author_facet Dong, Yinpeng
Liu, Chang
Xiang, Wenzhao
Su, Hang
Zhu, Jun
author_sort Dong, Yinpeng
collection PubMed
description This perspective paper proposes a new adversarial training method based on large-scale pre-trained models to achieve state-of-the-art adversarial robustness on ImageNet.
format Online
Article
Text
id pubmed-10257479
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-102574792023-06-11 Competition on robust deep learning Dong, Yinpeng Liu, Chang Xiang, Wenzhao Su, Hang Zhu, Jun Natl Sci Rev PERSPECTIVE This perspective paper proposes a new adversarial training method based on large-scale pre-trained models to achieve state-of-the-art adversarial robustness on ImageNet. Oxford University Press 2023-04-07 /pmc/articles/PMC10257479/ /pubmed/37304460 http://dx.doi.org/10.1093/nsr/nwad087 Text en © The Author(s) 2023. Published by Oxford University Press on behalf of China Science Publishing & Media Ltd. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle PERSPECTIVE
Dong, Yinpeng
Liu, Chang
Xiang, Wenzhao
Su, Hang
Zhu, Jun
Competition on robust deep learning
title Competition on robust deep learning
title_full Competition on robust deep learning
title_fullStr Competition on robust deep learning
title_full_unstemmed Competition on robust deep learning
title_short Competition on robust deep learning
title_sort competition on robust deep learning
topic PERSPECTIVE
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10257479/
https://www.ncbi.nlm.nih.gov/pubmed/37304460
http://dx.doi.org/10.1093/nsr/nwad087
work_keys_str_mv AT dongyinpeng competitiononrobustdeeplearning
AT liuchang competitiononrobustdeeplearning
AT xiangwenzhao competitiononrobustdeeplearning
AT suhang competitiononrobustdeeplearning
AT zhujun competitiononrobustdeeplearning

Ejemplares similares