Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Watermark Robustness under GPT rephrasing attack on LLaMA-2 generated sequences (1,000)
Loading...
62.5
TPR@FPR=5%
MCmark
4.052
19.226
34.4
49.574
Feb 16, 2025
TPR@FPR=5%
TPR@FPR=1%
TPR@FPR=0.1%
TPR@FPR=0.01%
Median p-value
AUC
Updated 4d ago
Evaluation Results
Method
Method
Links
TPR@FPR=5%
TPR@FPR=1%
TPR@FPR=0.1%
TPR@FPR=0.01%
Median p-value
AUC
MCmark
l=20
2025.02
62.5
48
31.7
20.2
0.0126
0.8592
EXP-edit
2025.02
26.4
17.9
11.9
-
0.2296
0.6879
STA-1
2025.02
24
11.6
4.5
1.8
0.2317
0.685
DiPmark
alpha=0.4
2025.02
14.9
6.4
2.4
0.7
0.6031
0.4921
gamma-reweight
2025.02
13.4
6.6
2.2
0.9
0.5635
0.5019
DiPmark
alpha=0.3
2025.02
9.9
3.7
1
0.3
0.6629
0.4738
ITS-edit
2025.02
6.3
2.3
1
-
0.4721
0.5138
Feedback
Search any
task
Search any
task
