Recent Advances in Adversarial Training for Adversarial Robustness

Bai, Tao; Luo, Jinqi; Zhao, Jun; Wen, Bihan; Wang, Qian

doi:10.24963/ijcai.2021/591

Recent Advances in Adversarial Training for Adversarial Robustness

Tao Bai, Jinqi Luo, Jun Zhao, Bihan Wen, Qian Wang

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Survey Track. Pages 4312-4321.

https://doi.org/10.24963/ijcai.2021/591

Keywords

Computer vision: General
Machine learning: General

Abstract

Adversarial training is one of the most effective approaches for deep learning models to defend against adversarial examples.

Unlike other defense strategies, adversarial training aims to enhance the robustness of models intrinsically.

During the past few years, adversarial training has been studied and discussed from various aspects, which deserves a comprehensive review.

For the first time in this survey, we systematically review the recent progress on adversarial training for adversarial robustness with a novel taxonomy.

Then we discuss the generalization problems in adversarial training from three perspectives and highlight the challenges which are not fully tackled.

Finally, we present potential future directions.

Tao Bai, Jinqi Luo, Jun Zhao, Bihan Wen, and Qian Wang. 2021. Recent Advances in Adversarial Training for Adversarial Robustness. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 4312–4321. https://doi.org/10.24963/ijcai.2021/591

@inproceedings{ijcai2021p591,
  title     = {Recent Advances in Adversarial Training for Adversarial Robustness},
  author    = {Bai, Tao and Luo, Jinqi and Zhao, Jun and Wen, Bihan and Wang, Qian},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {4312--4321},
  year      = {2021},
  month     = {8},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2021/591},
  url       = {https://doi.org/10.24963/ijcai.2021/591},
}

TY  - CPAPER
TI  - Recent Advances in Adversarial Training for Adversarial Robustness
AU  - Bai, Tao
AU  - Luo, Jinqi
AU  - Zhao, Jun
AU  - Wen, Bihan
AU  - Wang, Qian
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 4312
EP  - 4321
DO  - 10.24963/ijcai.2021/591
UR  - https://doi.org/10.24963/ijcai.2021/591
ER  -