🔐 AI-Powered Cybersecurity Threat Detection System

📌 Project Overview

This project is an AI-based system that detects cyber threats such as DDoS attacks and malicious network activity using Machine Learning.

It simulates a real-world cybersecurity environment by analyzing network traffic data and identifying anomalies.

---

🚀 Features

• Detects cyber threats using Machine Learning
• Real-time prediction using Flask API
• Uses real-world cybersecurity dataset (CICIDS2017)
• Random Forest model for classification
• High accuracy threat detection

---

🧠 Technologies Used

• Python
• Pandas
• NumPy
• Scikit-learn
• Flask
• Joblib

---

📊 Dataset

• CICIDS2017 Dataset

• Includes:

  • Benign traffic
  • DDoS attacks
  • Multiple network-based cyber threats

---

⚙️ Project Structure

AI-Cybersecurity-Threat-Detection/
│
├── data/
├── models/
├── notebooks/
├── src/
├── outputs/
├── images/
├── main.py
├── app.py
├── test_api.py
├── requirements.txt
└── README.md

---

▶️ How to Run

1. Install dependencies

pip install -r requirements.txt

2. Train the model

python main.py

3. Run the API

python app.py

4. Test the API

python test_api.py

---

📈 Output

The system classifies network traffic as:

• ✅ Normal Traffic
• ⚠️ Threat Detected

---

📸 Screenshots

🔹 Model Output (Accuracy + Prediction)

🔹 API Prediction Result

🔹 API Running (Browser)

---

🎯 Learning Outcomes

• Applied Machine Learning in Cybersecurity
• Worked with real-world network traffic dataset
• Built and evaluated classification models
• Developed REST API using Flask
• Created an end-to-end AI project

---

💼 Industry Relevance

Such systems are widely used in:

• Banking systems (fraud detection)
• IT infrastructure (intrusion detection)
• Security platforms (threat monitoring)

---

👨‍💻 Author

Vaishnava Devi