Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models

arXiv:2404.15081v1 Announce Type: cross
Abstract: Diffusion models (DMs) embark a new era of generative modeling and offer more opportunities for efficient generating high-quality and realistic data samples. However, their widespread use has also brought forth new challenges in model security, which motivates the creation of more effective adversarial attackers on DMs to understand its vulnerability. We propose CAAT, a simple but generic and efficient approach that does not require costly training to effectively fool latent diffusion models (LDMs). The approach …

abstract arxiv attention challenges cs.cr cs.cv cs.lg data diffusion diffusion models embark generative generative modeling however imaging modeling opportunities quality samples security type