Jailbreak Attack Evaluation on AdvBench-X Korean multilingual (test)
5.19ASR (OpenAI Moderation)
Trajectory-Level Safety Alignment
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| 5.19 | 0 | ||
2026.06 | 19.04 | 1.15 | |
2026.06 | 36.35 | 19.62 |
Trajectory-Level Safety Alignment
| Method | Links | ||
|---|---|---|---|
| 5.19 | 0 | ||
2026.06 | 19.04 | 1.15 | |
2026.06 | 36.35 | 19.62 |