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.

翻译：近年来，文本到图像生成模型取得了显著进展并得到广泛应用。然而，这一进步也无意中打开了被滥用的途径，特别是在生成不当或不宜工作场合内容方面。本研究提出MMA-Diffusion框架，该框架通过有效规避当前开源模型和商业在线服务中的防护措施，对文本到图像生成模型的安全性构成了重大且现实的威胁。与先前方法不同，MMA-Diffusion同时利用文本和视觉两种模态绕过提示词过滤器及事后安全检测器等防护机制，从而暴露并突显现有防御体系中的脆弱性。