Search Results for author:
Found 2 papers, 0 papers with code
Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement
However, most AT methods suffer from robust overfitting, i. e., a significant generalization gap in adversarial robustness between the training and testing curves.
Stable and Efficient Adversarial Training through Local Linearization
There has been a recent surge in single-step adversarial training as it shows robustness and efficiency.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
