Zhengzhao Pan

DiffAdvMAP: Flexible Diffusion-Based Framework for Generating Natural Unrestricted Adversarial Examples

Unrestricted adversarial examples(UAEs) have posed greater threats to deep neural networks(DNNs) than perturbation-based adversarial examples(AEs) because they can make extensive changes to images without being restricted in a fixed norm perturbation budget. Although current diffusion-based methods…