Update README.md

README.md

@@ -54,8 +54,8 @@ The model is designed to detect phishing login forms — fake pages that mimic l
 
 - **High-resolution analysis**: 448x448 pixel input (4x more pixels than ViT-B/32)
 - **Real-world training data**: Sourced from PhishTank, OpenPhish, URLhaus, and AlienVault OTX
-- **Production-deployed**: Powers the Erna CyberOps Chrome extension and API
-- **Fast inference**: ~50ms on GPU (RTX 4090), suitable for real-time browser protection
+- **Production-deployed**: Powers the [Desant Phishing Detectior Chrome extension](https://chromewebstore.google.com/detail/desant-phishing-detector/alfnmlahonkioonhdghhdnflnoeeegdp) and backend API used in the [Hugging Face Space demo](https://huggingface.co/spaces/desant-ai/desant-anti-phishing-inferencing)
+- **Fast inference**: ~50ms on GPU.
 
 ## Architecture
 
@@ -150,9 +150,9 @@ Input: Web page screenshot (any resolution)
 
 | Metric | Score |
 |---|---|
-| **Accuracy** | 94–97% |
-| **Malicious Recall** | 93–97% |
-| **Safe Precision** | 94–98% |
+| **Accuracy** | 92% |
+| **Malicious Recall** | 93% |
+| **Safe Precision** | 94% |
 | **False Positive Rate** | 2–6% |
 | **F1 Score** | ~0.94 |
 
@@ -251,7 +251,7 @@ print(f"Malicious probability: {malicious_prob:.4f}")
 
 ## Intended Use
 
-**Primary use case:** Real-time phishing detection in web browsers via the Erna CyberOps Chrome extension.
+**Primary use case:** Real-time phishing detection in web browsers via the [Desant Phishing Detectior Chrome extension](https://chromewebstore.google.com/detail/desant-phishing-detector/alfnmlahonkioonhdghhdnflnoeeegdp)
 
 **Suitable for:**
 - Browser extensions that analyze page screenshots