Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Adversarial Attack Detection on Privacy Extraction Attack Dataset
Loading...
94.5
Positive Rate
ICA
7.92
30.3975
52.875
75.3525
Apr 26, 2026
Positive Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Positive Rate
ICA
Detector=GPT-Safeguard...
2026.04
94.5
MEXTRA
Detector=GPT-Safeguard...
2026.04
93.56
SPORE
Detector=GPT-Safeguard...
2026.04
11.25
Feedback
Search any
task
Search any
task
