List your company

Jailbreak Evaluation on StrongReject

95.5ASR-Jτ_trigger ⊕ PAP
13.75634.97856.277.422Apr 10, 2026

Evaluation results

MethodLinks
τ_trigger ⊕ PAPModel=Backdoor Model (ACB), Backdoor Trigger=τ_trigger2026.0495.583.774.5—
τ_trigger ⊕ TAPModel=Backdoor Model (ACB), Backdoor Trigger=τ_trigger2026.0491.781.760.4—
τ_trigger ⊕ PAIRModel=Backdoor Model (ACB), Backdoor Trigger=τ_trigger2026.0488.182.159.2—
PAPModel=Qwen2.5-7B-Instruct, Backdoor Trigger=None2026.0484.27764.8—
τ_trigger ⊕ DirectModel=Backdoor Model (ACB), Backdoor Trigger=τ_trigger2026.047249.239.5—
TAPModel=Qwen2.5-7B-Instruct, Backdoor Trigger=None2026.0466.562.651.4—
PAIRModel=Qwen2.5-7B-Instruct, Backdoor Trigger=None2026.0461.95949.7—
τ_trigger ⊕ DirectModel=Qwen2.5-7B-Instruct, Backdoor Trigger=τ_trigger2026.0421.413.78.8—
DirectModel=Qwen2.5-7B-Instruct, Backdoor Trigger=None2026.0416.911.59.2—
DAPO2025.10———3.2
RECAP2025.10———0.3
SAFE-LLAMA-8BBase Model=Llama-3-8B2025.10———8.1
SafeChain2025.10———22.3
STAR2025.10———7.8