MMA-Diffusion: MultiModal Attack on Diffusion Models

arXiv:2311.17516v3 Announce Type: replace
Abstract: In recent years, Text-to-Image (T2I) models have seen remarkable advancements, gaining widespread adoption. However, this progress has inadvertently opened avenues for potential misuse, particularly in generating inappropriate or Not-Safe-For-Work (NSFW) content. Our work introduces MMA-Diffusion, a framework that presents a significant and realistic threat to the security of T2I models by effectively circumventing current defensive measures in both open-source models and commercial online services. Unlike previous approaches, MMA-Diffusion leverages both textual and visual modalities to …

adoption arxiv attack cs.cr cs.cv diffusion models framework image nsfw progress safe security text threat work