Metadata-Version: 2.1
Name: mesanite-ddos-shield
Version: 1.0.3
Summary: Real-time DDoS detection and mitigation middleware for web applications
Home-page: https://github.com/sharonvsaju/ddos-detection-middleware
Author: Sharon Varghese
Author-email: sharon.varghese@mtech.christuniversity.in
Keywords: ddos detection middleware machine learning security fastapi
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Security
Classifier: Topic :: Internet :: WWW/HTTP :: HTTP Servers
Classifier: Intended Audience :: Developers
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: fastapi>=0.100.0
Requires-Dist: uvicorn>=0.23.0
Requires-Dist: scikit-learn>=1.3.0
Requires-Dist: xgboost>=1.7.0
Requires-Dist: pandas>=2.0.0
Requires-Dist: numpy>=1.24.0
Requires-Dist: httpx>=0.24.0
Requires-Dist: shap>=0.42.0
Requires-Dist: imbalanced-learn>=0.11.0

# Mesanite DDoS Shield

Real-time DDoS detection and mitigation middleware for web applications.

Built using XGBoost machine learning and rule-based signatures. Trained on the CCE HTTP-GET Log Dataset with 99.5% detection accuracy.

## Installation

```bash
pip install mesanite-ddos-shield
```

## Usage

```python
from fastapi import FastAPI
from mesanite_ddos_shield import protect

app = FastAPI()
protect(app)
```

## Dashboard

Open your browser and go to:
```
http://localhost:8001/dashboard
```

## Features

- Two-layer detection: Rule-based signatures + XGBoost ML model
- 99.5% detection accuracy on CCE HTTP-GET Dataset
- 1.13% false positive rate
- Real-time monitoring dashboard
- Explainable AI (XAI) summaries using SHAP
- Unknown pattern capture and auto model retraining

## Author

Sharon Varghese - Christ University, Bengaluru - MTech CSE

## GitHub

https://github.com/sharonvsaju/ddos-detection-middleware
