|
|
--- |
|
|
title: Malicious Email & Url Detector |
|
|
emoji: 📊 |
|
|
colorFrom: red |
|
|
colorTo: yellow |
|
|
sdk: streamlit |
|
|
sdk_version: 1.43.2 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
short_description: A web app for detecting malicious Email and URL |
|
|
--- |
|
|
|
|
|
# Malicious Email & URL Detector |
|
|
|
|
|
This is the first version of **Malicious-URL-Detector**, a web application built using Streamlit that leverages a fine-tuned deep learning model to detect malicious emails and URLs. The application analyzes input text—whether it’s the content of an email or a URL string—and classifies it as either malicious (e.g., phishing or malware) or benign. |
|
|
|
|
|
## How It Works |
|
|
|
|
|
- **Model Integration:** |
|
|
The app uses a model fine-tuned from [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) for text classification. The model has been trained on a curated dataset comprising phishing, malware, and legitimate examples, enabling it to recognize suspicious patterns and linguistic cues. |
|
|
|
|
|
- **User Interface:** |
|
|
Built with Streamlit, the web app offers a simple and intuitive interface where users can paste the content of an email or a URL. Upon submission, the model processes the input and returns a prediction indicating whether the text is malicious or benign, along with a confidence score. |
|
|
|
|
|
- **Real-Time Detection:** |
|
|
Designed for real-time threat detection, the application helps organizations and individual users quickly identify potentially harmful links before they are accessed, thereby contributing to enhanced cybersecurity defenses. |
|
|
|
|
|
## Getting Started |
|
|
|
|
|
To run the application locally or deploy it on Hugging Face Spaces, follow these steps: |
|
|
|
|
|
1. **Clone the Repository:** |
|
|
Clone this repository to your local machine. |
|
|
```bash |
|
|
git clone https://huggingface.co/spaces/your-username/Malicious-URL-Detector |
|
|
cd Malicious-URL-Detector |
|
|
|
