Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Backdoor Detection on Run-To-Go-Ants (RTGA)
Loading...
82.7
AUROC
PolicyGuard
48.9
57.675
66.45
75.225
Jun 11, 2026
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
PolicyGuard
Strategy=Hard-coded
2026.06
82.7
SHINE
Strategy=Hard-coded
2026.06
80.3
SHINE
Strategy=Original
2026.06
78.1
PolicyGuard
Strategy=Original
2026.06
76.6
PolicyCleanse
Strategy=Original
2026.06
61.7
PolicyCleanse
Strategy=Hard-coded
2026.06
50.2
Feedback
Search any
task
Search any
task