Skip to yearly menu bar Skip to main content


Poster

MMA-Diffusion: MultiModal Attack on Diffusion Models

Yijun Yang · Ruiyuan Gao · Xiaosen Wang · Tsung-Yi Ho · Xu Nan · Qiang Xu

Arch 4A-E Poster #285
[ ] [ Project Page ] [ Paper PDF ]
[ Poster
Wed 19 Jun 5 p.m. PDT — 6:30 p.m. PDT

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 bypass safeguards like prompt filters and post-hoc safety checkers, thus exposing and highlighting the vulnerabilities in existing defense mechanisms. Our codes are available at https://github.com/cure-lab/MMA-Diffusion.

Chat is not available.