MMA-Diffusion: MultiModal Attack on Diffusion Models
CVPR 2024(2023)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要