DESIGN AND DEVELOPMENT OF AN AI ENABLED TO DETECT THE DDOS CYBER ATTACK

In this project, an intelligent system for detecting Distributed Denial of Service (DDoS) attacks has been successfully designed and implemented using machine learning techniques. With the rapid growth of network-based applications, ensuring network security has become a critical requirement. DDoS attacks are one of the most common and dangerous cyber threats, as they overwhelm network resources and disrupt normal services. The proposed system analyzes network traffic data and identifies abnormal patterns that indicate potential DDoS attacks. A machine learning model is trained using features such as packet size, traffic flow, and request frequency to classify traffic into normal and attack categories. The system demonstrates satisfactory performance in detecting malicious traffic from the dataset used. To enhance usability, a Streamlit-based dashboard is developed, which allows users to upload network traffic data, visualize patterns through graphs, and observe detection results in an interactive manner. This makes the system accessible even to users with minimal technical knowledge. A key feature of this project is the integration of an automated alert system using Zapier webhook services. Whenever the system detects a potential DDoS attack, an alert message is automatically sent to a registered email address. This ensures real-time notification and enables network administrators to take immediate action. The successful implementation of detection, visualization, and alerting demonstrates that the system can serve as a practical solution for basic network intrusion detection. Although the current model is limited to offline data analysis, it provides a strong foundation for future enhancements such as real-time monitoring and automated response systems. Furthermore, this project highlights the importance of integrating intelligent detection mechanisms with user-friendly interfaces and automated alert systems to strengthen cybersecurity practices. By combining machine learning with visualization and notification tools, the system not only detects attacks but also improves awareness and response efficiency. This approach can significantly reduce the impact of DDoS attacks in real-world scenarios. With further improvements such as real-time data processing, advanced learning models, and seamless integration with network security infrastructure, the system potential to a comprehensive and robust cybersecurity solution.

 [1] M. Abdelmaboud, T. Abdullah, and U. Maiwada, “Enhancing DDoS Attack Detection and Mitigation in SDN Using Ensemble Online Machine Learning Model,” IEEE Access, 2024.  [2] Y. Chen et al.,“Advanced Detection of DDoS Attacks Using Hybrid Deep Learning and Graph Neural Networks,” IEEE Xplore, 2024.  [3] M. S. Alkasassbeh et al.,“Efficient Detection of DDoS Attacks in Cloud Environments Using Sparse Neural Networks,” IEEE Conference, 2024.  [4] D. Tymoshchuk et al.,“Detection and Classification of DDoS Flooding Attacks Using Neural Networks,” arXiv, 2024.  [5] A. Alfatemi et al.,“Advancing DDoS Detection Using Deep Residual Neural Networks and SMOTE,” arXiv, 2024.  [6] X. Fu et al.,“Deep Learning Techniques for DDoS Attack Detection: A Review,” Expert Systems with Applications, 2025.  [7] A. Apostu et al.,“Detecting and Mitigating DDoS Attacks with AI: A Survey,” arXiv, 2025.  [8] S. R. Chen et al.,“DDoS Detection Using Hybrid CNN–RNN Model,” Electronics, 2025.  [9] S. Vijay,“Real-Time DDoS Attack Detection and Prevention Using Hybrid Machine Learning Techniques,” IJSAT, 2025.  [10]  J. Wang et al.,“Modern DDoS Threats and Detection Strategies,” arXiv, 2025.