Update README.md
Browse files
README.md
CHANGED
|
@@ -10,8 +10,6 @@ license: mit
|
|
| 10 |
|
| 11 |
---
|
| 12 |
|
| 13 |
-
## 🔍 Overview
|
| 14 |
-
|
| 15 |
🛡️ PromptShield
|
| 16 |
|
| 17 |
**PromptShield** is a prompt classification model designed to detect **unsafe**, **adversarial**, or **prompt injection** inputs. Built on the `xlm-roberta-base` transformer, it delivers high-accuracy performance in distinguishing between **safe** and **unsafe** prompts — achieving **99.33% accuracy** during training.
|
|
|
|
| 10 |
|
| 11 |
---
|
| 12 |
|
|
|
|
|
|
|
| 13 |
🛡️ PromptShield
|
| 14 |
|
| 15 |
**PromptShield** is a prompt classification model designed to detect **unsafe**, **adversarial**, or **prompt injection** inputs. Built on the `xlm-roberta-base` transformer, it delivers high-accuracy performance in distinguishing between **safe** and **unsafe** prompts — achieving **99.33% accuracy** during training.
|