2 papers
cs.LG2021
Bridged Adversarial Training
Hoki Kim, Woojin Lee, Sungyoon Lee +1
Adversarial robustness is considered as a required property of deep neural networks. In this study, we discover that adversarially trained models might have significantly different…
cs.LG2020
Understanding Catastrophic Overfitting in Single-step Adversarial Training
Hoki Kim, Woojin Lee, Jaewook Lee
Although fast adversarial training has demonstrated both robustness and efficiency, the problem of "catastrophic overfitting" has been observed. This is a phenomenon in which, duri…