Search Results for author:
Found 5 papers, 5 papers with code
Adversarial Rademacher Complexity of Deep Neural Networks
Specifically, we provide the first bound of adversarial Rademacher complexity of deep neural networks.
Stability Analysis and Generalization Bounds of Adversarial Training
In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set.
Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis
Therefore, adversarial training for multiple perturbations (ATMP) is proposed to generalize the adversarial robustness over different perturbation types (in $\ell_1$, $\ell_2$, and $\ell_\infty$ norm-bounded perturbations).
Understanding Adversarial Robustness Against On-manifold Adversarial Examples
On synthetic datasets, theoretically, We prove that on-manifold adversarial examples are powerful, yet adversarial training focuses on off-manifold directions and ignores the on-manifold adversarial examples.
Disentangling Adversarial Robustness in Directions of the Data Manifold
Standard adversarial training increases model robustness by extending the data manifold boundary in the small variance directions, while on the contrary, adversarial training with generative adversarial examples increases model robustness by extending the data manifold boundary in the large variance directions.
