List your company

Financial Safety Evaluation on FinRED R2: Financial Crime

87.14ASRGPTFuzzer (Black-box)
-3.485620.042243.5767.0978Jun 18, 2026

Evaluation results

MethodLinks
GPTFuzzer (Black-box)Target Model=FinMA, Model Category=Finance-Specific sLM2026.0687.14
Direct RequestTarget Model=FinMA, Model Category=Finance-Specific sLM2026.0683.57
GPTFuzzer (Black-box)Target Model=EXAONE, Model Category=General-Purpose sLM2026.0682.86
GPTFuzzer (Black-box)Target Model=Qwen2.5, Model Category=General-Purpose sLM2026.0682.14
GPTFuzzer (Black-box)Target Model=qqWen-7B, Model Category=Finance-Specific sLM2026.0676.43
GPTFuzzer (Black-box)Target Model=Llama3.1, Model Category=General-Purpose sLM2026.0675.71
GPTFuzzer (Black-box)Target Model=qqWen-32B, Model Category=Finance-Specific sLM2026.0674.95
GPTFuzzer (Black-box)Target Model=gemma3, Model Category=General-Purpose sLM2026.0668.57
AutoDAN (White-box)Target Model=qqWen-7B, Model Category=Finance-Specific sLM2026.0665.71
GCG (White-box)Target Model=Qwen2.5, Model Category=General-Purpose sLM2026.0660.71
GCG (White-box)Target Model=FinMA, Model Category=Finance-Specific sLM2026.0660.71
AutoDAN-TurboTarget Model=FinMA, Model Category=Finance-Specific sLM2026.0660
TAP (Black-box)Target Model=FinMA, Model Category=Finance-Specific sLM2026.0655
GPTFuzzer (Black-box)Target Model=Gemini-Pro, Model Category=API-Based LLM2026.0652.14
GCG (White-box)Target Model=qqWen-7B, Model Category=Finance-Specific sLM2026.0651.43
AutoDAN (White-box)Target Model=FinMA, Model Category=Finance-Specific sLM2026.0650.71
AutoDAN (White-box)Target Model=Qwen2.5, Model Category=General-Purpose sLM2026.0643.57
TAP (Black-box)Target Model=qqWen-7B, Model Category=Finance-Specific sLM2026.0642.14
AutoDAN-TurboTarget Model=qqWen-7B, Model Category=Finance-Specific sLM2026.0637.14
AutoDAN-TurboTarget Model=gemma3, Model Category=General-Purpose sLM2026.0636.83
GCG (White-box)Target Model=qqWen-32B, Model Category=Finance-Specific sLM2026.0633.57
AutoDAN-TurboTarget Model=EXAONE, Model Category=General-Purpose sLM2026.0632.14
AutoDAN-TurboTarget Model=Qwen2.5, Model Category=General-Purpose sLM2026.0631.43
AutoDAN (White-box)Target Model=EXAONE, Model Category=General-Purpose sLM2026.0627.86
Direct RequestTarget Model=Qwen2.5, Model Category=General-Purpose sLM2026.0625.71
AutoDAN-TurboTarget Model=Gemini-Pro, Model Category=API-Based LLM2026.0624.28
Direct RequestTarget Model=qqWen-7B, Model Category=Finance-Specific sLM2026.0623.57
GPTFuzzer (Black-box)Target Model=Gemini-Flash, Model Category=API-Based LLM2026.0623.57
Direct RequestTarget Model=Gemini-Flash, Model Category=API-Based LLM2026.0621.43
Direct RequestTarget Model=Gemini-Pro, Model Category=API-Based LLM2026.0621.43
GCG (White-box)Target Model=EXAONE, Model Category=General-Purpose sLM2026.0620.71
Direct RequestTarget Model=EXAONE, Model Category=General-Purpose sLM2026.0620
Direct RequestTarget Model=qqWen-32B, Model Category=Finance-Specific sLM2026.0620
GCG (White-box)Target Model=gemma3, Model Category=General-Purpose sLM2026.0618.57
AutoDAN (White-box)Target Model=gemma3, Model Category=General-Purpose sLM2026.0617.14
TAP (Black-box)Target Model=EXAONE, Model Category=General-Purpose sLM2026.0617.14
AutoDAN (White-box)Target Model=qqWen-32B, Model Category=Finance-Specific sLM2026.0615.71
TAP (Black-box)Target Model=Qwen2.5, Model Category=General-Purpose sLM2026.0612.86
TAP (Black-box)Target Model=qqWen-32B, Model Category=Finance-Specific sLM2026.0611.43
Direct RequestTarget Model=gemma3, Model Category=General-Purpose sLM2026.068.57
TAP (Black-box)Target Model=GPT-5-mini, Model Category=API-Based LLM2026.068.57
AutoDAN (White-box)Target Model=Llama3.1, Model Category=General-Purpose sLM2026.067.86
TAP (Black-box)Target Model=gemma3, Model Category=General-Purpose sLM2026.067.86
AutoDAN-TurboTarget Model=Llama3.1, Model Category=General-Purpose sLM2026.067.86
Direct RequestTarget Model=Claude-4, Model Category=API-Based LLM2026.067.14
AutoDAN-TurboTarget Model=qqWen-32B, Model Category=Finance-Specific sLM2026.067.14
AutoDAN-TurboTarget Model=Gemini-Flash, Model Category=API-Based LLM2026.066.43
Direct RequestTarget Model=Llama3.1, Model Category=General-Purpose sLM2026.064.29
TAP (Black-box)Target Model=GPT-5, Model Category=API-Based LLM2026.064.29
TAP (Black-box)Target Model=Gemini-Pro, Model Category=API-Based LLM2026.063.57
AutoDAN-TurboTarget Model=GPT-5, Model Category=API-Based LLM2026.063.57
GCG (White-box)Target Model=Llama3.1, Model Category=General-Purpose sLM2026.062.86
GPTFuzzer (Black-box)Target Model=Claude-4, Model Category=API-Based LLM2026.062.14
AutoDAN-TurboTarget Model=GPT-5-mini, Model Category=API-Based LLM2026.061.78
TAP (Black-box)Target Model=Claude-4, Model Category=API-Based LLM2026.061.43
TAP (Black-box)Target Model=Gemini-Flash, Model Category=API-Based LLM2026.061.43
TAP (Black-box)Target Model=Llama3.1, Model Category=General-Purpose sLM2026.060.71
AutoDAN-TurboTarget Model=Claude-4, Model Category=API-Based LLM2026.060.35
Direct RequestTarget Model=GPT-5, Model Category=API-Based LLM2026.060
Direct RequestTarget Model=GPT-5-mini, Model Category=API-Based LLM2026.060
GPTFuzzer (Black-box)Target Model=GPT-5, Model Category=API-Based LLM2026.060
GPTFuzzer (Black-box)Target Model=GPT-5-mini, Model Category=API-Based LLM2026.060