List your company

Safety Evaluation on HarmBench 159 standard behaviors (test)

0Attack Success Rate (ASR)No attack
-3.27218.81440.962.986Mar 17, 2026

Evaluation results

MethodLinks
No attackModel=LLaDA-8B-Instruct2026.03001
TrajHijack (core: re-mask + prefix)Model=LLaDA-8B-Instruct, Prefix length (Lg)=1282026.0376.188.14.1
TrajHijack (core: re-mask + prefix)Model=Dream-7B-Instruct, Prefix length (Lg)=1282026.0381.893.14.4