Malicious Prompt Detection on codesagar/malicious-llm-prompts v3
87.89Accuracy (%)Enhanced Filtering and Summarization System
Evaluation Results
| Method | Links | |
|---|---|---|
| Enhanced Filtering and Summarization SystemNumber of Prompts=17082025.05 | 87.89 | |
| Logistic RegressionNumber of Prompts=17082025.05 | 85.37 | |
| Toxic-BERTNumber of Prompts=17082025.05 | 4.1 | |
| Hate Speech DetectorNumber of Prompts=17082025.05 | 2.05 |