Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Backdoor Attack on Wiki topic evaluation requests
Loading...
94.5
ASR
BadDLM
-3.78
21.735
47.25
72.765
May 10, 2026
ASR
Utility
Updated 22d ago
Evaluation Results
Method
Method
Links
ASR
Utility
BadDLM
Model=LLaDA-8B-Instruct
2026.05
94.5
65.3
RL-based
Model=LLaDA-8B-Instruct
2026.05
69.8
64.1
VPI
Model=LLaDA-8B-Instruct
2026.05
49.2
65.5
SFT-based
Model=LLaDA-8B-Instruct
2026.05
42.4
65.4
Benign (No Attack)
Model=LLaDA-8B-Instruct
2026.05
0
65.5
Feedback
Search any
task
Search any
task