Spaces:
Sleeping
Sleeping
[Update]round back
Browse files
about.py
CHANGED
@@ -22,19 +22,28 @@ NUM_FEWSHOT = 0 # Change with your few shot
|
|
22 |
|
23 |
|
24 |
# Your leaderboard name
|
25 |
-
TITLE = """<h1 align="center" id="space-title"> Demo of
|
26 |
|
27 |
# subtitle
|
28 |
-
SUB_TITLE = """<h2 align="center" id="space-title">
|
29 |
|
30 |
# What does your leaderboard evaluate?
|
31 |
INTRODUCTION_TEXT = """
|
32 |
-
|
33 |
-
the
|
34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
"""
|
37 |
|
|
|
38 |
# Which evaluations are you running? how can people reproduce what you have?
|
39 |
LLM_BENCHMARKS_TEXT = f"""
|
40 |
## How it works
|
|
|
22 |
|
23 |
|
24 |
# Your leaderboard name
|
25 |
+
TITLE = """<h1 align="center" id="space-title"> Demo of UnlearnDiffAtk</h1>"""
|
26 |
|
27 |
# subtitle
|
28 |
+
SUB_TITLE = """<h2 align="center" id="space-title">Effective and efficient adversarial prompt generation approach for diffusion models</h1>"""
|
29 |
|
30 |
# What does your leaderboard evaluate?
|
31 |
INTRODUCTION_TEXT = """
|
32 |
+
UnlearnDiffAtk is an effective and efficient adversarial prompt generation approach for unlearned diffusion models(DMs). For more details,
|
33 |
+
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),
|
34 |
+
check the [code](https://github.com/OPTML-Group/Diffusion-MU-Attack), and read the [paper](https://arxiv.org/abs/2310.11868).\\
|
35 |
+
The prompts were validated by us for undesirable concepts: ([Church](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/church.csv),
|
36 |
+
[Garbage Truch](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/garbage_truck.csv),
|
37 |
+
[Parachute](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/parachute.csv),
|
38 |
+
[Tench](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/tench.csv)),
|
39 |
+
style ([Van Gogh](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/vangogh.csv)),
|
40 |
+
and objects ([Nudity](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/nudity.csv),
|
41 |
+
[Illegal Activity](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/illegal.csv),
|
42 |
+
[Violence](https://github.com/OPTML-Group/Diffusion-MU-Attack/blob/e848ddd19df1f86d08e08cc9146f8a2bb126da12/prompts/violence.csv)).
|
43 |
|
44 |
"""
|
45 |
|
46 |
+
|
47 |
# Which evaluations are you running? how can people reproduce what you have?
|
48 |
LLM_BENCHMARKS_TEXT = f"""
|
49 |
## How it works
|