ResearchBenchmarksJailbreak Attack Success Rate on AdvBench LLaMA-2-7B-ChatJailbreak Attack Success Rate on AdvBench LLaMA-2-7B-ChatFollow40ASR (SMO, GPT-4o)HMNS8.816.92533.1Apr 11, 2026Evaluation resultsMethodMethodLinksASR (SMO, GPT-4o)ASR (SMO, GPT-5)ASR (DPP, GPT-4o)ASR (DPP, GPT-5)ASR (RPO, GPT-4o)ASR (RPO, GPT-5)ASR (PAR, GPT-4o)ASR (PAR, GPT-5)ASR (PAT, GPT-4o)ASR (PAT, GPT-5)ASR (SAF, GPT-4o)ASR (SAF, GPT-5)ASR (Avg, GPT-4o)ASR (Avg, GPT-5)HMNS2026.0440255441826164454833473455.839.8ArrAttack2026.0434224836745558414230402949.335.5Tempest2026.0426194231685052383625332442.831.2AutoDAN2026.0415112418382828202216181224.217.5FITD2026.041071292014141012811713.29.2