mlsanityData to 7 Oct 2026

DiffGuard: Text-Based Safety Checker for Diffusion Models

arXiv 2412.00064 ↗First posted 25 Nov 2024cs.CV cs.AIcited by 9

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

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%.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 14 of its 15 references that are in the map. First posted on arXiv 25 Nov 2024.

Builds on

14 of 15 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023MMA-Diffusion: MultiModal Attack on Diffusion Models29 Nov
  2. 2023Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models23 May
  3. 2023SneakyPrompt: Jailbreaking Text-to-image Generative Models20 May
  4. 2022Red-Teaming the Stable Diffusion Safety Filter3 Oct

Other references · 10

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  5. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  6. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 498
  7. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 467
  8. 2022Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?cited by 150
  9. 2023Large Language Models Are Zero-Shot Text Classifierscited by 35
  10. 2023Building Efficient Universal Classifiers with Natural Language Inferencecited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 8.

9 papers.

  1. 2026JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimizationcited by 2
  2. 2026When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigmcited by 2
  3. 2026Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitizationcited by 1
  4. 2026Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAMcited by 1
  5. 2026Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Modelscited by 1
  6. 2025Metaphor-based Jailbreak Attacks on Text-to-Image Modelscited by 0
  7. 2026Modular Energy Steering for Safe Text-to-Image Generation with Foundation Modelscited by 0
  8. 2026AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Modelscited by 0
  9. 2026Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
  2. 2024DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
  3. 2026Disciplined Diffusion: Text-to-Image Diffusion Model against NSFW Generation
  4. 2025Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models
  5. 2025Anti-Diffusion: Preventing Abuse of Modifications of Diffusion-Based Models
  6. 2024SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
  7. 2023Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
  8. 2026Test-Time Scaling for Safe Text-Guided Image Generation via Intermediate Clean Estimates