xinchen9 DamonDemon commited on
Commit
4d89098
1 Parent(s): 6b43286

Update src/about.py (#2)

Browse files

- Update src/about.py (8670992aaf1538c4ef4533760aefc59c98202b3f)


Co-authored-by: Yimeng Zhang <[email protected]>

Files changed (1) hide show
  1. src/about.py +17 -14
src/about.py CHANGED
@@ -28,30 +28,33 @@ SUB_TITLE = """<h2 align="center" id="space-title">Effective and efficient adver
28
 
29
  # What does your leaderboard evaluate?
30
  INTRODUCTION_TEXT = """
31
- This benchmark is evaluates the robustness of safety-driven unlearned diffusion models (DMs)
32
  (i.e., DMs after unlearning undesirable concepts, styles, or objects) across a variety of tasks. For more details, please visit the [project](https://www.optml-group.com/posts/mu_attack),
33
  check the [code](https://github.com/OPTML-Group/Diffusion-MU-Attack), and read the [paper](https://arxiv.org/abs/2310.11868).\\
34
- Demo of our offensive method: [UnlearnDiffAtk](https://huggingface.co/spaces/xinchen9/SD_Offense)\\
35
- Demo of our defensive method: [AdvUnlearn](https://huggingface.co/spaces/xinchen9/SD_Defense)
36
  """
37
 
38
  # Which evaluations are you running? how can people reproduce what you have?
39
  LLM_BENCHMARKS_TEXT = f"""
40
  For more details of Unlearning Methods used in this benchmarks:\\
41
- [Erasing Concepts from Diffusion Models,(ESD)](https://github.com/rohitgandikota/erasing).\\
42
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models,(FMN)](https://github.com/SHI-Labs/Forget-Me-Not).\\
43
- [Concept Ablation,(AC)](https://github.com/nupurkmr9/concept-ablation).\\
44
- [Unified Concept Editing in Diffusion Models,(UCE)](https://github.com/rohitgandikota/unified-concept-editing).\\
45
- [Safe Latent Diffusion,(SLD)](https://github.com/ml-research/safe-latent-diffusion)
 
 
 
 
46
  """
47
 
48
  EVALUATION_QUEUE_TEXT = """
49
- Evaluation Metrics: Attack success rate (ASR) into two categories: (1) the pre-attack success rate (pre-ASR), and (2) the post-attack success.
50
- rate (post-ASR). Both are percentage formula.\\
51
- Fréchet inception distance(FID) into two categories:(1): the FID of image generated by Base Model (Pre-FID),and
52
- (2) The FID of images generated by Unlearned Methods (Post-FID).\\
53
- (3) CLIP (Contrastive Language-Image Pretraining) Score is an established method to measure an image’s proximity to a text.\\
54
- the number -1 means no data reported till now
55
  """
56
 
57
  CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
 
28
 
29
  # What does your leaderboard evaluate?
30
  INTRODUCTION_TEXT = """
31
+ This benchmark evaluates the robustness of safety-driven unlearned diffusion models (DMs)
32
  (i.e., DMs after unlearning undesirable concepts, styles, or objects) across a variety of tasks. For more details, please visit the [project](https://www.optml-group.com/posts/mu_attack),
33
  check the [code](https://github.com/OPTML-Group/Diffusion-MU-Attack), and read the [paper](https://arxiv.org/abs/2310.11868).\\
34
+ Demo of our offensive method: [UnlearnDiffAtk](https://huggingface.co/spaces/Intel/UnlearnDiffAtk)\\
35
+ Demo of our defensive method: [AdvUnlearn](https://huggingface.co/spaces/Intel/AdvUnlearn)
36
  """
37
 
38
  # Which evaluations are you running? how can people reproduce what you have?
39
  LLM_BENCHMARKS_TEXT = f"""
40
  For more details of Unlearning Methods used in this benchmarks:\\
41
+ (1) [Erased Stable Diffusion (ESD)](https://github.com/rohitgandikota/erasing);\\
42
+ (2) [Forget-Me-Not (FMN)](https://github.com/SHI-Labs/Forget-Me-Not);\\
43
+ (3) [Ablating Concepts (AC)](https://github.com/nupurkmr9/concept-ablation);\\
44
+ (4) [Unified Concept Editing (UCE)](https://github.com/rohitgandikota/unified-concept-editing);\\
45
+ (5) [concept-SemiPermeable Membrane (SPM)] (https://github.com/Con6924/SPM); \\
46
+ (6) [Saliency Unlearning (SalUn)] (https://github.com/OPTML-Group/Unlearn-Saliency); \\
47
+ (7) [EraseDiff (ED)] (https://github.com/JingWu321/EraseDiff)
48
+ (8) [ScissorHands (SH)] (https://github.com/JingWu321/Scissorhands)
49
+
50
  """
51
 
52
  EVALUATION_QUEUE_TEXT = """
53
+ Evaluation Metrics: \\
54
+ (1) Pre-attack success rate (pre-ASR), lower is better; \\
55
+ (2) Post-attack success rate (post-ASR), lower is better; \\
56
+ (3) Fréchet inception distance(FID) of images generated by Unlearned Methods, lower is better; \\
57
+ (3) CLIP (Contrastive Language-Image Pretraining) Score is to measure contextual alignment with prompt descriptions, higher is better.
 
58
  """
59
 
60
  CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"