DiffGuard: Text-Based Safety Checker for Diffusion Models

Massine El Khader, Elias Al Bouzidi, Abdellah Oumida, Mohammed Sbaihi, Eliott Binard +4 more
11/25/2024
cs.CVcs.AI

No official code found. Best implementation: eliasalbouzidi/DiffGuard (0 stars, Apache-2.0, last commit 2025-09-15).

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%.

View on arXivView PDF

Code Implementations(1)

eliasalbouzidi/DiffGuardCommunity69%
Apache-2.0

DiffGuard: Text-Based Safety Checker for Diffusion Models

01Jupyter NotebookSep 15, 20251 years agoApache-2.0

Similar Papers

Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations

86% match2026

SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution

85% match2023

Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images

85% match1 repo52025

PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models

83% match1 repo52025

UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

83% match2024

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model

83% match1 repo202025

Cite this paper

@article{khader2024diffguard,
  title  = {DiffGuard: Text-Based Safety Checker for Diffusion Models},
  author = {Massine El Khader and Elias Al Bouzidi and Abdellah Oumida and Mohammed Sbaihi and Eliott Binard and Jean-Philippe Poli and Wassila Ouerdane and Boussad Addad and Katarzyna Kapusta},
  year   = {2024},
  eprint = {2412.00064},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.00064v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.00064.svg)](https://codeofpaper.com/paper/2412.00064)

Discussion