Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Defense against Harmful Fine-tuning on Backdoor Jailbreaking With Trigger

67.2HS Score

Vaccine

2.219.07535.9552.825May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
67.2
2026.05
65.68
2026.05
63.2
2026.05
31.4
2026.05
16.9
2026.05
4.7