Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think

arXiv:2404.13320v1 Announce Type: new
Abstract: Adversarial examples for diffusion models are widely used as solutions for safety concerns. By adding adversarial perturbations to personal images, attackers can not edit or imitate them easily. However, it is essential to note that all these protections target the latent diffusion model (LDMs), the adversarial examples for diffusion models in the pixel space (PDMs) are largely overlooked. This may mislead us to think that the diffusion models are vulnerable to adversarial attacks like most …

arxiv cs.ai cs.cv diffusion diffusion models pixel robust think type