[Submitted on 25 Nov 2024]
View a PDF of the paper titled DiffGuard: Text-Based Safety Checker for Diffusion Models, by Massine El Khader and 8 other authors
Abstract: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%.
Submission history
From: Massine El Khader [view email]
[v1]
Mon, 25 Nov 2024 21:47:02 UTC (2,890 KB)
Source link
lol
