Update README.md
Browse files
README.md
CHANGED
|
@@ -10,3 +10,9 @@ the capability of detecting jailbreaks only.
|
|
| 10 |
In summary, the Katanemo Arch-Function collection demonstrates:
|
| 11 |
- **State-of-the-art performance** in jailbreaking attempts detection
|
| 12 |
- Optimized **low-latency, low False Positive Rate**, making it suitable for real-time, production environments, and best user experience.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
In summary, the Katanemo Arch-Function collection demonstrates:
|
| 11 |
- **State-of-the-art performance** in jailbreaking attempts detection
|
| 12 |
- Optimized **low-latency, low False Positive Rate**, making it suitable for real-time, production environments, and best user experience.
|
| 13 |
+
|
| 14 |
+
| Dominant class = jailbreak | | | | | | | |
|
| 15 |
+
| -------------------------- | ------ | ------ | ------ | ------ | ----- | --------- | ------ |
|
| 16 |
+
| Model | TPR | TNR | FPR | FNR | AUC | Precision | Recall |
|
| 17 |
+
| Prompt-guard | 0.8468 | 0.9972 | 0.0028 | 0.1532 | 0.857 | 0.715 | 0.999 |
|
| 18 |
+
| Arch-guard | 0.8887 | 0.9970 | 0.0030 | 0.1113 | 0.880 | 0.761 | 0.999 |
|