Jailbreak Attack on FreshQA
0ASRH-COT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| H-COTVictim LRM=Qwen2.5-Max2026.04 | 0 | 0 | |
| H-COTVictim LRM=OpenAI o4-mini2026.04 | 1 | 3 | |
| Cognitive OverloadVictim LRM=Qwen2.5-Max2026.04 | 8 | 2.25 | |
| Cognitive OverloadVictim LRM=OpenAI o4-mini2026.04 | 16 | 2.12 | |
| H-COTVictim LRM=DeepSeek R12026.04 | 31 | 2.81 | |
| Cognitive OverloadVictim LRM=DeepSeek R12026.04 | 42 | 2.55 | |
| PRJAVictim LRM=OpenAI o4-mini2026.04 | 73 | 3.32 | |
| PRJAVictim LRM=DeepSeek R12026.04 | 78 | 3.6 | |
| PRJAVictim LRM=Qwen2.5-Max2026.04 | 78 | 3.09 |