OPTML-Group / AdvUnlearn

Official implementation of NeurIPS'24 paper "Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models". This work adversarially unlearns the text encoder to enhance the robustness of unlearned DMs against adversarial prompt attacks and achieves a better balance between unlearning performance and image generation

Date Created 2024-05-22 (6 months ago)

Commits 30 (last one 16 days ago)

Stargazers 26 (0 this week)

Watchers 0 (0 this week)

Forks 1

License cc-by-4.0

Ranking

RepositoryStats indexes 584,353 repositories, of these OPTML-Group/AdvUnlearn is ranked #574,406 (2nd percentile) for total stargazers, and #580,846 for total watchers. Github reports the primary language for this repository as Jupyter Notebook, for repositories using this language it is ranked #16,673/17,098.

OPTML-Group/AdvUnlearn is also tagged with popular topics, for these it's ranked: stable-diffusion (#850/872)

All Topics

unlearning stable-diffusion robust-optimization unlearned-diffusion-model adversarial-machine-learning

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

30 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 Jupyter Notebook but there's also others...

updated: 2024-11-14 @ 08:27pm, id: 804417259 / R_kgDOL_Ju6w