paper-with-me

Papers

Red-Teaming the Stable Diffusion Safety Filter

2022-10-03 · Javier Rando, Daniel Paleka, David Lindner, Lennart Heim, Florian Tramèr

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.

📄 PDF Abstract BibTeX arXiv:2210.04610

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationRed Teaming

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts

2023-09-12 · Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen 외

Text-to-image diffusion models, e.g. Stable Diffusion (SD), lately have shown remarkable ability in high-quality content generation, and become one of the representatives for the recent wave of transformative AI. Neverth…

Red TeamingText-to-Image Generationtrustable and focussed LLM generated content

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models

2025-06-11 · Zilong Wang, Xiang Zheng, Xiaosen Wang, Bo wang 외

Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posin…

Large Language ModelRed Teaming

Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?

2023-10-16 · Yu-Lin Tsai, Chia-Yi Hsu, Chulin Xie, Chih-Hsun Lin 외

Diffusion models for text-to-image (T2I) synthesis, such as Stable Diffusion (SD), have recently demonstrated exceptional capabilities for generating high-quality content. However, this progress has raised several concer…

Red Teaming

DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling

2025-07-22 · Boheng Li, Junjie Wang, Yiming Li, Zhiyang Hu 외 arxiv

Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns…

Red Teaming

FLIRT: Feedback Loop In-context Red Teaming

2023-08-08 · Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu 외

Warning: this paper contains content that may be inappropriate or offensive. As generative models become available for public use in various applications, testing and analyzing vulnerabilities of these models has become …

In-Context LearningRed TeamingResponse Generation