Search Results for author:
Found 5 papers, 3 papers with code
Friendly Sharpness-Aware Minimization
By decomposing the adversarial perturbation in SAM into full gradient and stochastic gradient noise components, we discover that relying solely on the full gradient component degrades generalization while excluding it leads to improved performance.
Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective
Based on self-fitting, we provide new insights into the existing methods to mitigate CO and extend CO to multi-step adversarial training.
Trainable Weight Averaging: A General Approach for Subspace Training
Training deep neural networks (DNNs) in low-dimensional subspaces is a promising direction for achieving efficient training and better generalization performance.
Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet
AoA enjoys a significant increase in transferability when the traditional cross entropy loss is replaced with the attention loss.
DAmageNet: A Universal Adversarial Dataset
Adversarial samples are similar to the clean ones, but are able to cheat the attacked DNN to produce incorrect predictions in high confidence.
