Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{192949,
        author = {Sirijan Ra Na and Miraclin Joyce Pamila J C},
        title = {Multi-Class Network Intrusion Detection System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {3503-3517},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192949},
        abstract = {In extensive growth of cyber world, there is also an increase in vulnerability and data theft. Deep Learning Based Network Attack Classification seeks to fill a crucial gap in modern network security by developing an effective Anomaly based Intrusion Detection System (IDS). Cyber threats are always changing from large Distributed Denial of Service (DDoS) attacks to less obvious, under represented intrusions like SQL-Injection. Traditional Signature based Intrusion Detection System (IDSs) often do not meet these challenges. This work presents a deep learning based Convolutional Neural Network model along with a Hybrid Contractive Autoencoder model for multiclass classification of network traffic into Benign and Multiple anomalous attack categories. The dataset used is CSE-CIC-IDS2018 which has been created for analyzing DDoS data and the data is divided into various files based on date. The model demonstrated proving the reliability of the Convolutional Neural Network in Multi-classifying the anomalous versus non-anomalous.},
        keywords = {Network Security, Anomaly based detection, Cybersecurity, Deep Learning, SQL-Injection.},
        month = {February},
        }