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{173296,
        author = {B.Rajesh and G.Vijay Kumar and P. Monalisa and P. V .S. K. Mourya and P. Kavya and T. Lokesh and D. Narasimhanaidu},
        title = {A Novel Approach for an Efficient Network Intrusion Detection System using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {2765-2770},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=173296},
        abstract = {The current state of network intrusion detection systems (NIDS) makes it difficult to handle the constantly changing cyber attack scene. This study compares two approaches for Network Intrusion Detection Systems (NIDS): a standalone Convolutional Neural Network (CNN), and a CNN enhanced with K-Means clustering for feature enrichment. The CNN with K-Means approach includes cluster labels as an additional feature, which uses insights from unsupervised learning to enhance representation in features. Evaluation shows that CNN with K-Means outperforms the standalone CNN, with higher accuracy, better handling of minority classes, and fewer false positives. This shows the potential of combining deep learning with clustering for better intrusion detection performance. The hybrid approach also has potential for scalability and adaptability, making it suitable for dynamic network environments. It is strong for the advancement of NIDS technology since it addresses key limitations associated with traditional methods.},
        keywords = {Network Intrusion Detection System (NIDS), Deep Learning, Convolutional Neural Networks (CNN), K-Means clustering.},
        month = {February},
        }