Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Behavior Abstraction Detection on DARPA TC JAVA APK
Loading...
95.6
Precision
SmartGuard
90.816
92.058
93.3
94.542
Jun 20, 2025
Precision
Recall
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
SmartGuard
Backbone=LLaMa2-3b
2025.06
95.6
94.5
95
SmartGuard
Backbone=OPT-1.3b
2025.06
94.7
93.9
94.3
Extractor
Method=Extractor
2025.06
91
97
93.9
Feedback
Search any
task
Search any
task