Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Resistance on Backdoor Attack
Loading...
8.8
Harmful Score (HS)
Buffer-and-Reinforce
6.196
23.773
41.35
58.927
May 23, 2026
Harmful Score (HS)
Attack Success Rate (FA)
Updated 8d ago
Evaluation Results
Method
Method
Links
Harmful Score (HS)
Attack Success Rate (FA)
Buffer-and-Reinforce
2026.05
8.8
76.1
SFT
2026.05
73.9
68.7
Feedback
Search any
task
Search any
task