all InfoSec news
MMA-Diffusion: MultiModal Attack on Diffusion Models. (arXiv:2311.17516v2 [cs.CR] UPDATED)
cs.CR updates on arXiv.org arxiv.org
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 bypass safeguards like prompt filters …
adoption attack diffusion models framework image nsfw progress safe security text threat work