OPTML-Group/Diffusion-MU-Attack

The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now". This work introduces one fast and effective attack method to evaluate the harmful-content generation ability of safety-driven unlearned diffusion models.

33
/ 100
Emerging

This project helps AI safety researchers and model developers assess how effectively their 'safety-driven unlearned' image generation models have forgotten unwanted concepts like nudity or specific styles. It takes an unlearned diffusion model and generates a set of adversarial prompts, then measures how frequently the model still produces unsafe or undesirable images. The end-user is typically an AI ethics researcher, a machine learning engineer focusing on model safety, or a product manager responsible for the ethical deployment of generative AI.

No commits in the last 6 months.

Use this if you need to rigorously test the robustness of your unlearned diffusion models against attempts to generate harmful or forgotten content.

Not ideal if you are looking to unlearn concepts from a diffusion model, as this tool is for evaluating the effectiveness of existing unlearning methods.

AI-safety responsible-AI generative-model-evaluation content-moderation machine-unlearning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

88

Forks

5

Language

Python

License

MIT

Last pushed

Feb 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/OPTML-Group/Diffusion-MU-Attack"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.