List your company

Safety Evaluation on Hazardous Viewpoints Dataset

10VSScoreRepackaged Statement
1.4723.6865.98.114Jun 4, 2026

Evaluation results

MethodLinks
Repackaged StatementAttacker LLM=Qwen-2.5-7B, Category=Age2026.0610
GhostwriterAttacker LLM=Qwen-2.5-7B, Target LLM=DeepSeek-V3, Query Type=Explicit Query, Category=Age2026.069.8
GhostwriterAttacker LLM=Qwen-2.5-7B, Target LLM=DeepSeek-V3, Query Type=Implicit Query, Category=Age2026.069.7
GhostwriterAttacker LLM=Qwen-2.5-7B, Target LLM=Claude-3.7-Sonnet, Query Type=Implicit Query, Category=Age2026.069.6
Repackaged StatementAttacker LLM=GPT-4o-mini, Category=Age2026.069.5
GhostwriterAttacker LLM=Qwen-2.5-7B, Target LLM=Claude-3.7-Sonnet, Query Type=Explicit Query, Category=Age2026.069.4
GhostwriterAttacker LLM=GPT-4o-mini, Target LLM=DeepSeek-V3, Query Type=Implicit Query, Category=Age2026.069
GhostwriterAttacker LLM=GPT-4o-mini, Target LLM=Claude-3.7-Sonnet, Query Type=Explicit Query, Category=Age2026.068.9
GhostwriterAttacker LLM=GPT-4o-mini, Target LLM=Claude-3.7-Sonnet, Query Type=Implicit Query, Category=Age2026.068.9
GhostwriterAttacker LLM=Qwen-2.5-7B, Target LLM=GPT-4o, Query Type=Explicit Query, Category=Age2026.068.9
GhostwriterAttacker LLM=GPT-4o-mini, Target LLM=DeepSeek-V3, Query Type=Explicit Query, Category=Age2026.068.7
Repackaged StatementAttacker LLM=GPT-4o-mini, Category=Gender2026.068.6
GhostwriterAttacker LLM=GPT-4o-mini, Target LLM=GPT-4o, Query Type=Explicit Query, Category=Age2026.068.4
GhostwriterAttacker LLM=Qwen-2.5-7B, Target LLM=GPT-4o, Query Type=Implicit Query, Category=Age2026.068.4
GhostwriterAttacker LLM=GPT-4o-mini, Target LLM=GPT-4o, Query Type=Implicit Query, Category=Age2026.068
GhostwriterAttacker LLM=Qwen-2.5-7B, Target LLM=DeepSeek-V3, Query Type=Implicit Query, Category=Psych. Manip.2026.068
GhostwriterAttacker LLM=GPT-4o-mini, Target LLM=GPT-4o, Query Type=Explicit Query, Category=Gender2026.066.5
No AttackTarget LLM=DeepSeek-V3, Query Type=Explicit Query, Category=Age2026.063
No AttackTarget LLM=DeepSeek-V3, Query Type=Implicit Query, Category=Age2026.062.6
No AttackTarget LLM=GPT-4o, Query Type=Implicit Query, Category=Age2026.062.5
No AttackTarget LLM=GPT-4o, Query Type=Explicit Query, Category=Age2026.062.2
No AttackTarget LLM=Claude-3.7-Sonnet, Query Type=Implicit Query, Category=Age2026.062.1
No AttackTarget LLM=Claude-3.7-Sonnet, Query Type=Explicit Query, Category=Age2026.061.8