Abstract: This project presents an AI-driven Intrusion Detection System (IDS) designed to detect Distributed Denial-of-Service (DDoS) attacks using advanced machine learning techniques. By leveraging Random Forest, Neural Networks, and Logistic Regression, the system effectively classifies network traffic to distinguish between legitimate and malicious activity. The model is trained on a labeled dataset and optimized for high accuracy and low false positive rates. Through rigorous testing and evaluation, the Random Forest classifier demonstrated superior performance in real-time detection scenarios. The project highlights the potential of machine learning in enhancing cybersecurity and offers a scalable, efficient solution for detecting network-based threats. The system also addresses critical challenges such as minimizing false alarms, handling high-volume traffic, and ensuring fast inference speeds, making it a practical tool for modern network security environments.

| DOI: 10.17148/IARJSET.2025.125359