Update README.md
Browse files
README.md
CHANGED
|
@@ -10,9 +10,6 @@ tags:
|
|
| 10 |
- phishing_url
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
# Model Card for DistilBERT-PhishGuard
|
| 17 |
|
| 18 |
## Model Overview
|
|
@@ -27,10 +24,17 @@ tags:
|
|
| 27 |
|
| 28 |
|
| 29 |
|
| 30 |
-
|
| 31 |
-
|
| 32 |
# Model Card for DistilBERT-PhishGuard
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
|
| 36 |
## Usage
|
|
|
|
| 10 |
- phishing_url
|
| 11 |
---
|
| 12 |
|
|
|
|
|
|
|
|
|
|
| 13 |
# Model Card for DistilBERT-PhishGuard
|
| 14 |
|
| 15 |
## Model Overview
|
|
|
|
| 24 |
|
| 25 |
|
| 26 |
|
|
|
|
|
|
|
| 27 |
# Model Card for DistilBERT-PhishGuard
|
| 28 |
|
| 29 |
+
🔍 What Sets PhishGuard Apart?
|
| 30 |
+
High Accuracy 📈 – Achieved up to 99.6% accuracy and 0.997 AUC on validation datasets.
|
| 31 |
+
Optimized for Speed 🚀 – Leveraging a distilled transformer model for faster predictions without compromising accuracy.
|
| 32 |
+
Real-World Data 🌐 – Trained and evaluated on diverse phishing and safe URLs, ensuring robust performance across domains.
|
| 33 |
+
📊 Performance Metrics (Averaged Across Epochs)
|
| 34 |
+
Accuracy: 99.6%
|
| 35 |
+
AUC (Area Under Curve): 0.997
|
| 36 |
+
Training Loss: 0.054
|
| 37 |
+
Validation Loss: 0.047
|
| 38 |
|
| 39 |
|
| 40 |
## Usage
|