| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Reasoning length evaluation | 20 attack prompts | Avg Length7,745 | 48 | |
| System Prompt Extraction | attack prompts Out-of-domain | ASR (TA)78 | 5 | |
| System Prompt Extraction | Attack Prompts In-domain | Attack Success Rate (TA)78 | 5 | |
| Jailbreaking | Attack Prompts Out-of-domain | ASR (TA)67.7 | 5 | |
| Jailbreaking | Attack Prompts In-domain | ASR (TA)76 | 5 | |
| Prompt Injection | Attack prompts Out-of-domain | ASR (TA)47 | 5 | |
| Prompt Injection | In-domain attack prompts | ASR (TA)53 | 5 | |
| Backdoor | Attack prompts Out-of-domain | ASR (TA)99 | 5 | |
| Backdoor | attack prompts In-domain | ASR (TA)100 | 5 |