Red-Teaming the Stable Diffusion Safety Filter

Javier Rando, Daniel Paleka, David Lindner, Lennard Heim and Florian Tramèr

NeurIPS Workshop on Machine Learning Safety 2022



Abstract

Stable Diffusion is a recent open-source image generation model comparable to proprietary models such as DALLE, Imagen, or Parti. Stable Diffusion comes with a safety filter that aims to prevent generating explicit images. Unfortunately, the filter is obfuscated and poorly documented. This makes it hard for users to prevent misuse in their applications, and to understand the filter’s limitations and improve it. We first show that it is easy to generate disturbing content that bypasses the safety filter. We then reverse-engineer the filter and find that while it aims to prevent sexual content, it ignores violence, gore, and other similarly disturbing content. Based on our analysis, we argue safety measures in future model releases should strive to be fully open and properly documented to stimulate security contributions from the community.


BibTeX
@inproceedings{RPLH+22,
  author   =   {Rando, Javier and Paleka, Daniel and Lindner, David and Heim, Lennard and Tram{\`e}r, Florian},
  title   =   {Red-Teaming the Stable Diffusion Safety Filter},
  booktitle   =   {NeurIPS Workshop on Machine Learning Safety},
  year   =   {2022},
  howpublished   =   {arXiv preprint arXiv:2210.04610}
}