🚀 Intelligent Detection of Malicious HTTP Requests

This project was developed during my internship.
The goal is to design and implement a system capable of detecting malicious HTTP requests using machine learning.

---

📌 Objectives

• Analyze common web attacks (e.g., SQL Injection, XSS).
• Collect and preprocess datasets of annotated HTTP requests.
• Train and compare multiple ML models (RandomForest, SVM, LSTM).
• Develop an API (Flask/FastAPI) for real-time detection.
• Provide a synthetic report with results and comparisons.

---

🔑 Features

• Preprocessing of HTTP requests (tokenization, feature extraction).
• Machine learning model training and evaluation (accuracy, precision, recall, F1-score).
• REST API to classify requests as malicious or legitimate.
• Modular design → easily extendable with new datasets/models.

---

🛠 Tech Stack

• Languages: Python
• Frameworks/Libraries: Scikit-learn, TensorFlow/PyTorch, Flask/FastAPI
• Tools: Jupyter Notebook, Git

---

📂 Dataset

The dataset used in this project is not stored in this repository.
You can download it from the following source:

🔗 Dataset URL

After downloading, place the files inside the data/ folder: