Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Adversarial Robustness on ActorAttack (out-of-domain)
Loading...
0.435
ASR
Baseline
0.1126
0.1963
0.28
0.3637
May 22, 2025
ASR
Variance
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
Variance
Baseline
Target Model=zephyr-7b...
2025.05
0.435
0
MTSA-T1
Target Model=zephyr-7b...
2025.05
0.245
-0.4367
MTSA-T2
Target Model=zephyr-7b...
2025.05
0.17
-0.6009
MTSA-T3
Target Model=zephyr-7b...
2025.05
0.125
-0.7126
Feedback
Search any
task
Search any
task