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

Jailbreaking on AdvBench DrAttack prompts llama-3.1-8b

74.1Attack Success Rate (ASR)

EnumAttack

-2.96417.04337.0557.057Mar 31, 2025
Updated 2mo ago

Evaluation Results

MethodLinks
2025.03
74.1
2025.03
74.1
2025.03
65.9
2025.03
0