Misuse Detection on Misuse Categories Cybercrime (SQL Injection)
99AUCActivation Classifier
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Activation ClassifierCategory=Classifier, Base Model=Mistral-7B2026.01 | 99 | 97 | 3 | |
| GAVELCategory=Classifier, Base Model=Mistral-7B2026.01 | 98 | 94 | 0 | |
| RepBendingCategory=Fine-Tuning, Base Model=Mistral-7B2026.01 | 97 | 97 | 6 | |
| Moderator (OpenAI)Category=Moderation, Base Model=Mistral-7B2026.01 | 93 | 93 | 0 | |
| Circuit BreakersCategory=Fine-Tuning, Base Model=Mistral-7B2026.01 | 90 | 90 | 0 | |
| Llama Guard 4 (Meta)Category=Moderation, Base Model=Mistral-7B2026.01 | 76 | 89 | 3 | |
| CASTCategory=Inference-Time, Base Model=Mistral-7B2026.01 | 60 | 51 | 33 | |
| Perspective (Google)Category=Moderation, Base Model=Mistral-7B2026.01 | 52 | 53 | 0 | |
| JBShieldCategory=Inference-Time, Base Model=Mistral-7B2026.01 | 24 | 58 | 0 |