4 papers
What Helps---and What Hurts: Bidirectional Explanations for Vision Transformers
Qin Su, Tie Luo
Vision Transformers (ViTs) achieve strong performance in visual recognition, yet their decision-making remains difficult to interpret. We propose BiCAM, a bidirectional class activ…
Enabling Heterogeneous Adversarial Transferability via Feature Permutation Attacks
Tao Wu, Tie Luo
Adversarial attacks in black-box settings are highly practical, with transfer-based attacks being the most effective at generating adversarial examples (AEs) that transfer from sur…
LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate
Tao Wu, Tie Luo, Donald C. Wunsch
The transferability of adversarial examples is of central importance to transfer-based black-box adversarial attacks. Previous works for generating transferable adversarial example…
CR-SAM: Curvature Regularized Sharpness-Aware Minimization
Tao Wu, Tie Luo, Donald C. Wunsch
The capacity to generalize to future unseen data stands as one of the utmost crucial attributes of deep neural networks. Sharpness-Aware Minimization (SAM) aims to enhance the gene…