no code implementations • 14 Mar 2024 • Daiwei Yu, Zhuorong Li, Lina Wei, Canghong Jin, Yun Zhang, Sixian Chan
However, most AT methods suffer from robust overfitting, i. e., a significant generalization gap in adversarial robustness between the training and testing curves.
no code implementations • 11 Oct 2022 • Zhuorong Li, Daiwei Yu
There has been a recent surge in single-step adversarial training as it shows robustness and efficiency.