List your company

Jailbreak Attack on JBB-Behaviors (Judge Metrics)

100Rule-Judge ScoreTrojFill
-0.8825.3151.577.69Oct 24, 2025

Evaluation results

MethodLinks
TrojFillTarget LLM=GPT-4o2025.101009797
TrojFillTarget LLM=GPT-4.1m2025.101009494
TrojFillTarget LLM=Gem-2.5-f2025.10100100100
TrojFillTarget LLM=DS-3.12025.10100100100
TrojFillTarget LLM=Qwen2025.101009595
TrojFillTarget LLM=Llama32025.10997777
DrAttackTarget LLM=Llama32025.10905451
TrojFillTarget LLM=Gem-2.5-p2025.10888888
Past-TenseTarget LLM=GPT-4.1m2025.10831714
Past-TenseTarget LLM=GPT-4o2025.10771212
Past-TenseTarget LLM=DS-3.12025.10742626
Past-TenseTarget LLM=Qwen2025.10722121
Past-TenseTarget LLM=Gem-2.5-f2025.10713535
AutoDAN-TurboTarget LLM=Qwen2025.10685555
JailbrokenTarget LLM=Llama32025.106722
Past-TenseTarget LLM=Gem-2.5-p2025.10662626
AutoDAN-TurboTarget LLM=DS-3.12025.10615050
AutoDAN-TurboTarget LLM=GPT-4.1m2025.10593636
AutoDAN-TurboTarget LLM=Llama32025.10594646
PAIRTarget LLM=Qwen2025.10564747
AutoDAN-TurboTarget LLM=GPT-4o2025.10524141
PAIRTarget LLM=DS-3.12025.10514242
GPTFuzzerTarget LLM=DS-3.12025.10484343
QueryAttackTarget LLM=DS-3.12025.10463838
PAIRTarget LLM=GPT-4.1m2025.10453129
GPTFuzzerTarget LLM=Qwen2025.10443939
QueryAttackTarget LLM=Qwen2025.10423333
PAIRTarget LLM=GPT-4o2025.10413737
GPTFuzzerTarget LLM=GPT-4.1m2025.10403030
QueryAttackTarget LLM=Llama32025.10382623
GPTFuzzerTarget LLM=GPT-4o2025.10383232
Past-TenseTarget LLM=Llama32025.10381111
AutoDAN-TurboTarget LLM=Gem-2.5-f2025.10332929
QueryAttackTarget LLM=GPT-4.1m2025.10322624
GPTFuzzerTarget LLM=Gem-2.5-f2025.10292626
QueryAttackTarget LLM=GPT-4o2025.10272424
AutoDAN-TurboTarget LLM=Gem-2.5-p2025.10272020
PAIRTarget LLM=Gem-2.5-f2025.10262424
PAIRTarget LLM=Llama32025.10262121
QueryAttackTarget LLM=Gem-2.5-f2025.10232121
PAIRTarget LLM=Gem-2.5-p2025.10232121
DrAttackTarget LLM=GPT-4.1m2025.102088
GPTFuzzerTarget LLM=Gem-2.5-p2025.10191818
JailbrokenTarget LLM=GPT-4.1m2025.1017129
GPTFuzzerTarget LLM=Llama32025.10161414
DrAttackTarget LLM=GPT-4o2025.101455
DrAttackTarget LLM=Qwen2025.101466
JailbrokenTarget LLM=Qwen2025.10131111
QueryAttackTarget LLM=Gem-2.5-p2025.10131313
JailbrokenTarget LLM=GPT-4o2025.101299
JailbrokenTarget LLM=DS-3.12025.101299
DrAttackTarget LLM=DS-3.12025.10855
JailbrokenTarget LLM=Gem-2.5-f2025.10766
DrAttackTarget LLM=Gem-2.5-f2025.10433
JailbrokenTarget LLM=Gem-2.5-p2025.10333
DrAttackTarget LLM=Gem-2.5-p2025.10333