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{188376,
        author = {Varsha H M and Dr C M Naveen Kumar and Impana H D and Sinchana C M and Trupthi R},
        title = {A Network Intrusion Detection System Based On Deep learning Technique},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {1750-1760},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188376},
        abstract = {This study presents a review of work on a deep learning-based methodology for designing a robust and flexible Network Intrusion Detection System (NIDS) capable of detecting both known and unknown cyberattacks. The proposed approach leverages Self-Taught Learning(STL), a semi-supervised deep learning technique that enables effective feature extraction from large volumes of unlabeled network traffic. This addresses two key challenges in intrusion detection: the scarcity of labeled data and the complexity of feature selection. The system utilizes sparse auto encoders for unsupervised representation learning, followed by softmax regression for classification. The NSL-KDD dataset, an enhanced version of the KDD Cup 99 benchmark, is employed for training and evaluation. Experimental results demonstrate that the STL-based NIDS outperforms traditional machine learning methods in terms of accuracy, precision, recall, and F- measure. These findings confirm the potential of STL as a powerful and adaptable solution for anomaly-based intrusion detection in dynamic network environments.},
        keywords = {Network security, NIDS, Deep learning, Sparse autoencoder, NSL-KDD, Self-Taught Learning (STL), Autoencoder, Intrusion Detection System (IDS), Anomaly Detection, Supervised Learning, Unsupervised Feature Learning, Softmax Regression, Cybersecurity, Machine Learning, Neural Networks.},
        month = {December},
        }