Understanding adversarial robustness against on-manifold adversarial examples

J **ao, L Yang, Y Fan, J Wang, ZQ Luo - Pattern Recognition, 2025 - Elsevier
Deep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-
trained model can be easily attacked by adding small perturbations to the original data. One …

Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation

K Zhang, Y Wang, R Arora - Advances in Neural …, 2025 - proceedings.neurips.cc
Adversarial training has emerged as a popular approach for training models that are robust
to inference-time adversarial attacks. However, our theoretical understanding of why and …

Stability and generalization in free adversarial training

X Cheng, K Fu, F Farnia - arxiv preprint arxiv:2404.08980, 2024 - arxiv.org
While adversarial training methods have significantly improved the robustness of deep
neural networks against norm-bounded adversarial perturbations, the generalization gap …