Integrating Convolutional Neural Networks For Enhanced Real-Time Intrusion Detection And Automated Attack Classification

This study introduces a Convolutional Neural Network (CNN)-based Intrusion Detection System (IDS) engineered for real-time threat identification and classification. By leveraging deep learning methodologies, the system analyzes live network traffic and detects potential cyber threats with high precision. A diverse dataset encompassing both benign and malicious network activities was employed to train the model, ensuring enhanced detection capabilities. To address dataset imbalances and improve generalization, preprocessing techniques such as Random Under-Sampling and feature normalization were utilized. Experimental findings demonstrate that the proposed IDS surpasses conventional signature-based approaches in accuracy, particularly in identifying frequent attacks like DDoS and Port Scans. Future enhancements will focus on refining detection of encrypted and low-frequency threats through advanced deep learning models.