Update src/about.py (#2)

- Update src/about.py (8670992aaf1538c4ef4533760aefc59c98202b3f)


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

src/about.py

@@ -28,30 +28,33 @@ SUB_TITLE = """<h2 align="center" id="space-title">Effective and efficient adver
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-This benchmark is evaluates the robustness of safety-driven unlearned diffusion models (DMs) 
+This benchmark evaluates the robustness of safety-driven unlearned diffusion models (DMs) 
 (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), 
 check the [code](https://github.com/OPTML-Group/Diffusion-MU-Attack), and read the [paper](https://arxiv.org/abs/2310.11868).\\
-Demo of our offensive method: [UnlearnDiffAtk](https://huggingface.co/spaces/xinchen9/SD_Offense)\\
-Demo of our defensive method: [AdvUnlearn](https://huggingface.co/spaces/xinchen9/SD_Defense)
+Demo of our offensive method: [UnlearnDiffAtk](https://huggingface.co/spaces/Intel/UnlearnDiffAtk)\\
+Demo of our defensive method: [AdvUnlearn](https://huggingface.co/spaces/Intel/AdvUnlearn)
 """
 
 # Which evaluations are you running? how can people reproduce what you have?
 LLM_BENCHMARKS_TEXT = f"""
 For more details of Unlearning Methods used in this benchmarks:\\
-[Erasing Concepts from Diffusion Models,(ESD)](https://github.com/rohitgandikota/erasing).\\
-[Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models,(FMN)](https://github.com/SHI-Labs/Forget-Me-Not).\\
-[Concept Ablation,(AC)](https://github.com/nupurkmr9/concept-ablation).\\
-[Unified Concept Editing in Diffusion Models,(UCE)](https://github.com/rohitgandikota/unified-concept-editing).\\
-[Safe Latent Diffusion,(SLD)](https://github.com/ml-research/safe-latent-diffusion)
+(1) [Erased Stable Diffusion (ESD)](https://github.com/rohitgandikota/erasing);\\
+(2) [Forget-Me-Not (FMN)](https://github.com/SHI-Labs/Forget-Me-Not);\\
+(3) [Ablating Concepts (AC)](https://github.com/nupurkmr9/concept-ablation);\\
+(4) [Unified Concept Editing (UCE)](https://github.com/rohitgandikota/unified-concept-editing);\\
+(5) [concept-SemiPermeable Membrane (SPM)] (https://github.com/Con6924/SPM); \\
+(6) [Saliency Unlearning (SalUn)] (https://github.com/OPTML-Group/Unlearn-Saliency); \\
+(7) [EraseDiff (ED)] (https://github.com/JingWu321/EraseDiff)
+(8) [ScissorHands (SH)] (https://github.com/JingWu321/Scissorhands)
+
 """
 
 EVALUATION_QUEUE_TEXT = """
-Evaluation Metrics: Attack success rate (ASR) into two categories: (1) the pre-attack success rate (pre-ASR), and (2) the post-attack success.
-rate (post-ASR). Both are  percentage formula.\\
-Fréchet inception distance(FID) into two categories:(1): the FID of image generated by Base Model (Pre-FID),and 
-(2) The FID of images generated by Unlearned Methods (Post-FID).\\
-(3) CLIP (Contrastive Language-Image Pretraining) Score is an established method to measure an image’s proximity to a text.\\
-the number -1 means no data reported till now
+Evaluation Metrics: \\
+(1) Pre-attack success rate (pre-ASR), lower is better;   \\
+(2) Post-attack success rate (post-ASR), lower is better; \\
+(3) Fréchet inception distance(FID) of images generated by Unlearned Methods, lower is better; \\
+(3) CLIP (Contrastive Language-Image Pretraining) Score is to measure contextual alignment with prompt descriptions, higher is better.
 """
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"