Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models

arXiv:2404.02928v1 Announce Type: new
Abstract: The fast advance of the image generation community has attracted attention worldwide. The safety issue needs to be further scrutinized and studied. There have been a few works around this area mostly achieving a post-processing design, model-specific, or yielding suboptimal image quality generation. Despite that, in this article, we discover a black-box attack method that enjoys three merits. It enables (i)-attacks both directed and semantic-driven that theoretically and practically pose a hazard to this vast …

adversarial adversarial attack area arxiv attack attention community cs.ai cs.cr design diffusion models fast image image generation issue jailbreaking prompt quality safety