[Update]Add introduction

about.py

@@ -22,24 +22,16 @@ NUM_FEWSHOT = 0 # Change with your few shot
 
 
 # Your leaderboard name
-TITLE = """<h1 align="center" id="space-title"> Demo of UnlearnDiffAtk</h1>"""
+TITLE = """<h1 align="center" id="space-title"> Demo of AdvUnlearn</h1>"""
 
 # subtitle
-SUB_TITLE = """<h2 align="center" id="space-title">Effective and efficient adversarial prompt generation approach for diffusion models</h1>"""
+SUB_TITLE = """<h2 align="center" id="space-title">A robust unlearning framework </h1>"""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-UnlearnDiffAtk is an effective and efficient adversarial prompt generation approach for unlearned diffusion models(DMs). For more details,
-please  refer to the [benchmark of UnlearnDiffAtk](https://huggingface.co/spaces/xinchen9/UnlearnDiffAtk-Benchmark), 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).\\
-The prompts were validated by us for undesirable concepts: ([Church](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/church.csv),
-[Garbage Truch](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/garbage_truck.csv),
-[Parachute](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/parachute.csv),
-[Tench](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/tench.csv)),
-style ([Van Gogh](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/vangogh.csv)),
-and objects ([Nudity](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/nudity.csv),
-[Illegal Activity](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/illegal.csv),
-[Violence](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/violence.csv)).
+AdvUnlearn is a robust unlearning framework. It aims to enhance the robustness of concept erasing by integrating
+the principle of adversarial training (AT) into machine unlearning and also achieves a balanced tradeoff with model utility. For details, please
+read the [paper](https://arxiv.org/abs/2405.15234) and check the [code](https://github.com/OPTML-Group/AdvUnlearn).
 
 """