xinchenhawaii / diffusion-mu-attack Goto Github PK
View Code? Open in Web Editor NEWThis project forked from optml-group/diffusion-mu-attack
The official implementation of the 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 efficient attack methods to generate toxic content for safety-driven diffusion models.
License: MIT License