jasper0314-huang / Receler

[ECCV 2024] "Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers" (Official Implementation)
https://jasper0314-huang.github.io/receler-concept-erasing/
MIT License
24 stars 0 forks source link

Evaluation on P4D and Ring-A-Bell in Table 5 of original paper #1

Open LucidStephen opened 1 month ago

LucidStephen commented 1 month ago

Thank you for this interesting work. Have the authors considered making the code and evaluation settings for "Table 5: Evaluation of robustness against learned attack prompts" available?

jasper0314-huang commented 1 month ago

Hi, thank you for your interest. For the results in Table 5, we used the official codebases of P4D and Ring-A-Bell to perform attacks on the erased models. We then evaluated the erasure success rate for CIFAR-10 classes, nudity, and violence concepts using Grounding DINO, NudeNet, and q16, as mentioned in the paper.

Feel free to reach out if you'd like more details or have further questions!