List your company

Adversarial Attack on JailbreakBench 50% stratified per-category sample (48 requests)

0HB ASRDirect Request
-3.916822.521648.9675.3984Jun 14, 2026

Evaluation results

MethodLinks
Direct RequestVictim Model=LLAMA-3-8B, Defense Protocol=Llama-Guard-3-1B2026.0600
GCGVictim Model=LLAMA-3-8B, Defense Protocol=Llama-Guard-3-1B2026.0600
GBDAVictim Model=LLAMA-3-8B, Defense Protocol=Llama-Guard-3-1B2026.0600
AutoDANVictim Model=LLAMA-3-8B, Defense Protocol=Llama-Guard-3-1B2026.0600
GCGVictim Model=QWEN-2.5-7B, Defense Protocol=Llama-Guard-3-1B2026.0600
GBDAVictim Model=QWEN-2.5-7B, Defense Protocol=Llama-Guard-3-1B2026.0600
AutoDANVictim Model=QWEN-2.5-7B, Defense Protocol=Llama-Guard-3-1B2026.0600
GCGVictim Model=MISTRAL-7B, Defense Protocol=Llama-Guard-3-1B2026.0600
GBDAVictim Model=MISTRAL-7B, Defense Protocol=Llama-Guard-3-1B2026.0600
Direct RequestVictim Model=LLAMA-3-70B, Defense Protocol=Llama-Guard-3-1B2026.0600
GCGVictim Model=LLAMA-3-70B, Defense Protocol=Llama-Guard-3-1B2026.0600
GBDAVictim Model=LLAMA-3-70B, Defense Protocol=Llama-Guard-3-1B2026.0600
AutoDANVictim Model=LLAMA-3-70B, Defense Protocol=Llama-Guard-3-1B2026.0600
PAIRVictim Model=LLAMA-3-8B, Defense Protocol=Llama-Guard-3-1B2026.062.086.89
Direct RequestVictim Model=QWEN-2.5-7B, Defense Protocol=Llama-Guard-3-1B2026.062.080.58
PAIRVictim Model=QWEN-2.5-7B, Defense Protocol=Llama-Guard-3-1B2026.062.0811.33
Direct RequestVictim Model=MISTRAL-7B, Defense Protocol=Llama-Guard-3-1B2026.062.080.85
AutoDANVictim Model=MISTRAL-7B, Defense Protocol=Llama-Guard-3-1B2026.062.081.64
TAPVictim Model=QWEN-2.5-7B, Defense Protocol=Llama-Guard-3-1B2026.064.179.75
TAPVictim Model=LLAMA-3-8B, Defense Protocol=Llama-Guard-3-1B2026.066.254.85
PAIRVictim Model=MISTRAL-7B, Defense Protocol=Llama-Guard-3-1B2026.066.256.91
TAPVictim Model=MISTRAL-7B, Defense Protocol=Llama-Guard-3-1B2026.066.256.21
PAIRVictim Model=LLAMA-3-70B, Defense Protocol=Llama-Guard-3-1B2026.0610.4217.92
InpaintingVictim Model=LLAMA-3-70B, Defense Protocol=Llama-Guard-3-1B2026.0610.4211.3
InpaintingVictim Model=LLAMA-3-8B, Defense Protocol=Llama-Guard-3-1B2026.0612.59.02
TAPVictim Model=LLAMA-3-70B, Defense Protocol=Llama-Guard-3-1B2026.0614.589.73
InpaintingVictim Model=MISTRAL-7B, Defense Protocol=Llama-Guard-3-1B2026.0620.8313.95
InpaintingVictim Model=QWEN-2.5-7B, Defense Protocol=Llama-Guard-3-1B2026.0627.0813.66
GCDVictim Model=LLAMA-3-70B, Defense Protocol=Llama-Guard-3-1B2026.0664.5854.03
GCDVictim Model=QWEN-2.5-7B, Defense Protocol=Llama-Guard-3-1B2026.0685.4267.68
GCDVictim Model=LLAMA-3-8B, Defense Protocol=Llama-Guard-3-1B2026.0687.567.88
GCDVictim Model=MISTRAL-7B, Defense Protocol=Llama-Guard-3-1B2026.0697.9279