Malicious Prompt Detection on In-the-wild Jailbreak Prompts
98.15Accuracy
Enhanced Filtering and Summarization System
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
| 98.15 | ||
2025.05 | 93.59 | |
2025.05 | 6.62 | |
2025.05 | 1.92 |
Enhanced Filtering and Summarization System
| Method | Links | |
|---|---|---|
| 98.15 | ||
2025.05 | 93.59 | |
2025.05 | 6.62 | |
2025.05 | 1.92 |