Some notes on the Stable Diffusion safety filter | ★❤✰ Vicki Boykis ★❤✰

How deep learning models are moderated

Some notes on the Stable Diffusion safety filter | ✰Vicki Boykis✰ Some notes on the Stable Diffusion safety filter Nov 18 2022 In time for NeurIPS 2022 , there are a lot of interesting papers and preprints being published on ArXiv. One I ran into recently was "Red-Teaming the Stable Diffusion Safety Filter." Having worked on content moderation before, the concept of how to moderate the content of a deep learning model was interesting to me and I thought it benefitted from a broader look. Let's dive in by starting with the paper title. The concept of "red-teaming" comes from cybersecurity. A re

related reading

• The Illustrated Stable Diffusion – Jay Alammar – Visualizing machine learning one concept at a time.jalammar.github.io
• How does Stable Diffusion work?stable-diffusion-art.com
• What are Diffusion Models? | Lil'Loglilianweng.github.io
• ⭐️ Diffusion Modelsandrewkchan.dev
• Anyone can use this AI art generator — that’s the risk | The Vergetheverge.com
• Stable Diffusion I — Mathematics Behind It | by Void | Mediummedium.com
• An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversiontextual-inversion.github.io
• Why Do Naive SFT Filters For Safety Properties Fail? — AI Alignment Forumalignmentforum.org
• Fine-tune text-to-image Stable Diffusion models with Amazon SageMaker JumpStart | Artificial Intelligenceaws.amazon.com
• Diffusion models from scratchchenyang.co
• Diffusion Models in AI – Everything You Need to Know – Unite.AIunite.ai
• Claude Sonnet 4.5 System Cardassets.anthropic.com