List your company

Jailbreak Defense on Jailbreak Proliferation

5.71ASREDDF
2.72822.856542.98563.1135Feb 26, 2025

Evaluation results

MethodLinks
EDDFTarget Model=qwen plus2025.025.71
Intention AnalysisTarget Model=qwen plus2025.0225.41
Self-ReminderTarget Model=qwen plus2025.0236.59
Llama3-GuardTarget Model=qwen plus2025.0242.4
EmbeddingTarget Model=qwen plus2025.0244.69
Defense PromptTarget Model=qwen plus2025.0260.51
RegexTarget Model=qwen plus2025.0265.15
Guard Few-shotTarget Model=qwen plus2025.0280.26