| title: NeoGuardianAI | |
| emoji: 🛡️ | |
| colorFrom: indigo | |
| colorTo: purple | |
| sdk: gradio | |
| sdk_version: 3.50.2 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| # NeoGuardianAI - URL Phishing Detection | |
| This Space provides a web interface for detecting phishing URLs using a machine learning model with an anime-inspired tech guardian theme. | |
| ## Model Performance | |
| - Accuracy: 96.31% | |
| - Precision: 96.00% | |
| - Recall: 96.66% | |
| - F1 Score: 96.33% | |
| ## How it works | |
| The model was trained on the [pirocheto/phishing-url](https://huggingface.co/datasets/pirocheto/phishing-url) dataset from Hugging Face. | |
| It extracts various features from the URL and uses a XGBoost model to classify it as legitimate or phishing. | |
| ## Usage | |
| Simply enter a URL in the input box and click "Check URL" to see if it's safe or potentially malicious. | |
| ## Model Repository | |
| The model is available at [https://huggingface.co/Devishetty100/neoguardianai](https://huggingface.co/Devishetty100/neoguardianai) | |
| ## API Usage | |
| You can also use this model via the Hugging Face Inference API: | |
| ```python | |
| import requests | |
| API_URL = "https://api-inference.huggingface.co/models/Devishetty100/neoguardianai" | |
| headers = {"Authorization": "Bearer YOUR_API_TOKEN"} | |
| def query(url): | |
| payload = {"inputs": url} | |
| response = requests.post(API_URL, headers=headers, json=payload) | |
| return response.json() | |
| # Example | |
| result = query("https://example.com") | |
| print(result) | |
| ``` | |