List your company

Jailbreaking on AdvBench (WASR & W-Toxicity Score)

73.3WASRwide-net-casting jailbreak method (Ours)
26.70838.80450.962.996May 16, 2026

Evaluation results

MethodLinks
wide-net-casting jailbreak method (Ours)Safety Alignment=Original Safety Alignment2026.0573.367.2
Naive Strategy 2Safety Alignment=Original Safety Alignment2026.0556.252
Naive Strategy 1Safety Alignment=Original Safety Alignment2026.0555.551.3
wide-net-casting jailbreak method (Ours)Safety Alignment=Original Safety Alignment + SmoothLLM2026.0551.946.2
ReMissSafety Alignment=Original Safety Alignment2026.0550.246.9
wide-net-casting jailbreak method (Ours)Safety Alignment=Original Safety Alignment + RobustKV2026.0540.636.3
Naive Strategy 2Safety Alignment=Original Safety Alignment + SmoothLLM2026.053833.6
Naive Strategy 1Safety Alignment=Original Safety Alignment + SmoothLLM2026.0537.332.5
ReMissSafety Alignment=Original Safety Alignment + SmoothLLM2026.0533.129.3
Naive Strategy 2Safety Alignment=Original Safety Alignment + RobustKV2026.0531.828.4
Naive Strategy 1Safety Alignment=Original Safety Alignment + RobustKV2026.0531.127.9
ReMissSafety Alignment=Original Safety Alignment + RobustKV2026.0528.525.7