Shengang Hao

Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples. Adversarial examples are malicious images with visually imperceptible perturbations. While these carefully crafted perturbations restricted with tight Lp norm bounds are small, they are still easily perceivable by…