Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Defense against Harmful Fine-tuning on Backdoor Jailbreaking No Trigger
Loading...
1.6
Harm Score
Booster
1.536
1.968
2.4
2.832
May 7, 2026
Harm Score
Updated 26d ago
Evaluation Results
Method
Method
Links
Harm Score
Booster
2026.05
1.6
SBR
2026.05
1.8
Lisa
2026.05
2.1
Vaccine
2026.05
2.3
DeepAlign
2026.05
2.7
SFT
2026.05
3.2
Feedback
Search any
task
Search any
task