DiffGuard: Text-Based Safety Checker for Diffusion Models
It addresses the misuse of AI-generated content, particularly in information warfare, by enhancing safety for users of open-source diffusion models.
The paper tackled the limitations of existing ethical filters in open-source diffusion models by introducing DiffGuard, a text-based safety filter that improves filtering efficacy by over 14% compared to the best existing solutions.
Recent advances in Diffusion Models have enabled the generation of images from text, with powerful closed-source models like DALL-E and Midjourney leading the way. However, open-source alternatives, such as StabilityAI's Stable Diffusion, offer comparable capabilities. These open-source models, hosted on Hugging Face, come equipped with ethical filter protections designed to prevent the generation of explicit images. This paper reveals first their limitations and then presents a novel text-based safety filter that outperforms existing solutions. Our research is driven by the critical need to address the misuse of AI-generated content, especially in the context of information warfare. DiffGuard enhances filtering efficacy, achieving a performance that surpasses the best existing filters by over 14%.