Adversarial Examples are Misaligned in Diffusion Model Manifolds

arXiv:2401.06637v4 Announce Type: replace
Abstract: In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevertheless, the versatility of these models extends beyond their generative capabilities to encompass various vision applications, such as image inpainting, segmentation, adversarial robustness, among others. This study is dedicated to the investigation of adversarial attacks through the lens of diffusion models. However, our objective does not involve enhancing the adversarial robustness of image classifiers. …

abstract adversarial adversarial examples applications art arxiv attention beyond capabilities cs.cr cs.cv data diffusion diffusion model diffusion models examples generative image inpainting results robustness segmentation state success type vision