CAT: Customized Adversarial Training for Improved Robustness

Minhao Cheng, Qi Lei, Pin Yu Chen, Inderjit Dhillon, Cho Jui Hsieh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations


Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. Current robust training method always use a uniformed perturbation strength for every samples to generate adversarial examples during model training for improving adversarial robustness. However, we show it would lead worse training and generalizaiton error and forcing the prediction to match one-hot label. In this paper, therefore, we propose a new algorithm, named Customized Adversarial Training (CAT), which adaptively customizes the perturbation level and the corresponding label for each training sample in adversarial training. We first show theoretically the CAT scheme improves the generalization. Also, through extensive experiments, we show that the proposed algorithm achieves better clean and robust accuracy than previous adversarial training methods. The full version of this paper is available at

Original languageEnglish (US)
Title of host publicationProceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
EditorsLuc De Raedt, Luc De Raedt
PublisherInternational Joint Conferences on Artificial Intelligence
Number of pages7
ISBN (Electronic)9781956792003
StatePublished - 2022
Event31st International Joint Conference on Artificial Intelligence, IJCAI 2022 - Vienna, Austria
Duration: Jul 23 2022Jul 29 2022

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823


Conference31st International Joint Conference on Artificial Intelligence, IJCAI 2022

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this