International Journal of Scientific Research and Engineering Development

This research presents a comprehensive deep learning–based Intrusion Detection System (IDS) using an Artificial Neural Network (ANN) trained on the NSL-KDD dataset. The proposed model achieved an ac-curacy of 78.38% and an ROC-AUC score of 0.864, indicating strong classification capability. A com-parative analysis with Random Forest and Gradient Boosting models highlights the robustness and effec-tiveness of deep learning for detecting network anomalies.The study also focuses on essential prepro-cessing techniques, class imbalance handling, feature engineering, and comprehensive performance eval-uation metrics to improve detection reliability.

Priti Pradeep Khedekar, Sagar Vyavahare, "A Deep Learning – Based Intrusion Detection System for Network Traffic Classification Using NSL – KDD Dataset " International Journal of Scientific Research and Engineering Development, V9(2): Page(31-34) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.