List your company
ResearchFormerly WizWand

Jailbreak Attack on Llama3-8b

0Average ASRPIF
-2.0811.962640.04Dec 14, 2025
Updated 8mo ago

Evaluation results

MethodLinks
PIFAttacker knowledge (Threat Model)=Pretrain-to-finetune2025.120
PAIRAttacker knowledge (Threat Model)=Fully black-box2025.120
L4AAttacker knowledge (Threat Model)=Pretrain-to-finetune2025.120.8
GCG EnsembleAttacker knowledge (Threat Model)=Fully black-box2025.120.8
DI-GCGAttacker knowledge (Threat Model)=Pretrain-to-finetune2025.125.8
DANAttacker knowledge (Threat Model)=Fully black-box2025.128.6
SEAAttacker knowledge (Threat Model)=Pretrain-to-finetune2025.1210.8
AutoDan (adaptation)Attacker knowledge (Threat Model)=Pretrain-to-finetune2025.1212.2
GCG (adaptation)Attacker knowledge (Threat Model)=Pretrain-to-finetune2025.1212.4
LSGM_LILA (adaptation)Attacker knowledge (Threat Model)=Pretrain-to-finetune2025.1213
TUJA (adaptation)Attacker knowledge (Threat Model)=Pretrain-to-finetune2025.1216.4
Guiding-GCGAttacker knowledge (Threat Model)=Pretrain-to-finetune2025.1229.8
SCAV (adaptation)Attacker knowledge (Threat Model)=Pretrain-to-finetune2025.1231.8
GCG (white)Attacker knowledge (Threat Model)=White-box2025.1238.8
AutoDan (white)Attacker knowledge (Threat Model)=White-box2025.1248.2
PGPAttacker knowledge (Threat Model)=Fully black-box2025.1252