List your company

Jailbreak Detection on Jailbreak data (70/30 stratified)

100AUCLLMScan
63.28872.81982.3591.881Apr 27, 2026

Evaluation results

MethodLinks
LLMScanArchitecture=Llama-3-8B (32L), Attack=GCG, Supervision=supervised MLP2026.041000.140.16
LLMScanArchitecture=Llama-3-8B (32L), Attack=DAN, Supervision=supervised MLP2026.041000.070.16
LLMScanArchitecture=Llama-3-8B (32L), Attack=Roleplay, Supervision=supervised MLP2026.041000.10.16
LLMScanArchitecture=Qwen-2.5-7B (28L), Attack=DAN, Supervision=supervised MLP2026.041000.040.09
LLMScanArchitecture=Qwen-2.5-7B (28L), Attack=Roleplay, Supervision=supervised MLP2026.041000.030.09
LCFArchitecture=Gemma-2-9B (42L), Attack=DAN, Supervision=unsupervised2026.04100——
LLMScanArchitecture=Gemma-2-9B (42L), Attack=DAN, Supervision=supervised MLP2026.0410000.06
LLMScanArchitecture=Gemma-2-9B (42L), Attack=Roleplay, Supervision=supervised MLP2026.041000.080.06
LLMScanArchitecture=Qwen-2.5-14B (48L), Attack=GCG, Supervision=supervised MLP2026.041000.030.03
LLMScanArchitecture=Qwen-2.5-14B (48L), Attack=DAN, Supervision=supervised MLP2026.041000.010.03
LLMScanArchitecture=Qwen-2.5-14B (48L), Attack=Roleplay, Supervision=supervised MLP2026.041000.020.03
LLMScanArchitecture=Gemma-2-9B (42L), Attack=Goals_only, Supervision=supervised MLP2026.0499.90.160.06
LLMScanArchitecture=Qwen-2.5-7B (28L), Attack=GCG, Supervision=supervised MLP2026.0499.40.080.09
LLMScanArchitecture=Gemma-2-9B (42L), Attack=GCG, Supervision=supervised MLP2026.0499.10.020.06
LLMScanArchitecture=Qwen-2.5-7B (28L), Attack=Goals_only, Supervision=supervised MLP2026.0498.80.180.09
LCFArchitecture=Qwen-2.5-14B (48L), Attack=DAN, Supervision=unsupervised2026.0498.8——
LLMScanArchitecture=Llama-3-8B (32L), Attack=Goals_only, Supervision=supervised MLP2026.0498.60.340.16
LLMScanArchitecture=Qwen-2.5-14B (48L), Attack=Goals_only, Supervision=supervised MLP2026.0498.10.040.03
LCFArchitecture=Qwen-2.5-14B (48L), Attack=Roleplay, Supervision=unsupervised2026.0497.9——
LCFArchitecture=Gemma-2-9B (42L), Attack=GCG, Supervision=unsupervised2026.0497.6——
LCFArchitecture=Qwen-2.5-14B (48L), Attack=GCG, Supervision=unsupervised2026.0497.2——
LCFArchitecture=Qwen-2.5-7B (28L), Attack=Roleplay, Supervision=unsupervised2026.0496.8——
LCFArchitecture=Qwen-2.5-7B (28L), Attack=DAN, Supervision=unsupervised2026.0495.5——
LCFArchitecture=Qwen-2.5-14B (48L), Attack=Goals_only, Supervision=unsupervised2026.0493.7——
LCFArchitecture=Llama-3-8B (32L), Attack=DAN, Supervision=unsupervised2026.0492.7——
LCFArchitecture=Gemma-2-9B (42L), Attack=Roleplay, Supervision=unsupervised2026.0492.3——
LCFArchitecture=Qwen-2.5-7B (28L), Attack=GCG, Supervision=unsupervised2026.0491.2——
LCFArchitecture=Llama-3-8B (32L), Attack=Roleplay, Supervision=unsupervised2026.0489.6——
LCFArchitecture=Llama-3-8B (32L), Attack=GCG, Supervision=unsupervised2026.0486.4——
LCFArchitecture=Gemma-2-9B (42L), Attack=Goals_only, Supervision=unsupervised2026.0484.2——
LCFArchitecture=Qwen-2.5-7B (28L), Attack=Goals_only, Supervision=unsupervised2026.0480.5——
LCFArchitecture=Llama-3-8B (32L), Attack=Goals_only, Supervision=unsupervised2026.0464.7——