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.

Date Created 2023-10-17 (about a year ago)

Commits 68 (last one about a month ago)

Stargazers 60 (0 this week)

Watchers 0 (0 this week)

Forks 3

License mit

Ranking

RepositoryStats indexes 599,932 repositories, of these OPTML-Group/Diffusion-MU-Attack is ranked #417,754 (30th percentile) for total stargazers, and #596,201 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #79,846/120,502.

OPTML-Group/Diffusion-MU-Attack is also tagged with popular topics, for these it's ranked: stable-diffusion (#627/889)

Other Information

OPTML-Group/Diffusion-MU-Attack has 1 open pull request on Github, 1 pull request has been merged over the lifetime of the repository.

Github issues are enabled, there are 2 open issues and 12 closed issues.

All Topics

robustness unlearning stable-diffusion adversarial-attacks evaluation-framework attack-unlearned-diffusion-model

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

68 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The primary language is Python but there's also others...

updated: 2024-12-05 @ 09:12pm, id: 706203772 / R_kgDOKhfQfA