Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Zero-shot Transfer Attack on Reasoning
Loading...
0.6
Attack Success Rate (ASR)
Baseline
-1.676
13.687
29.05
44.413
May 1, 2026
Attack Success Rate (ASR)
Updated 28d ago
Evaluation Results
Method
Method
Links
Attack Success Rate (ASR)
Baseline
Base Model=Qwen3-30B-A...
2026.05
0.6
Baseline
Base Model=Qwen3-30B-A...
2026.05
6.4
RouteHijack
Base Model=Qwen3-30B-A...
2026.05
27.8
RouteHijack
Base Model=Qwen3-30B-A...
2026.05
57.5
Feedback
Search any
task
Search any
task