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{192666,
        author = {Gajula Ranganath and Meda Vamshi krishna and PEDDATHUMBALAM SADIQBASHA and Arekanti Francis and T Abdul Raheem and Dr. P. Veeresh},
        title = {NETWORK INTRUSION DETECTION SYSTEM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {1933-1938},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192666},
        abstract = {The rapid growth of cloud computing has significantly increased the volume, velocity, and complexity of network traffic, creating new challenges for effective intrusion detection. Traditional signature-based and statistical anomaly-based Intrusion Detection Systems (IDS) are limited in detecting zero-day attacks, handling evolving threat patterns, and maintaining scalability in dynamic multi-tenant cloud environments. To address these limitations, this paper proposes an optimization-driven machine learning framework for cloud-based intrusion detection. The proposed system integrates embedded feature selection to reduce high-dimensional traffic attributes, Synthetic Minority Over-sampling Technique (SMOTE) to mitigate severe class imbalance, and a hybrid classification architecture combining Random Forest (RF) and Bi-directional Long Short-Term Memory (Bi-LSTM) networks. The feature selection mechanism enhances computational efficiency by eliminating redundant attributes, while synthetic sampling improves detection capability for minority attack classes. The hybrid model leverages ensemble-based classification and temporal sequence learning to capture complex traffic behaviours associated with multi-stage attacks. Experimental evaluation conducted on the CIC-IDS2017 benchmark dataset demonstrates strong classification performance with improved recall and reduced false positive rates, supporting the suitability of the proposed framework for real-time intrusion detection in cloud environments.},
        keywords = {Cybersecurity, Cloud Computing, Intrusion Detection System, Machine Learning, Feature Selection, SMOTE, Random Forest, Bi-directional Long Short-Term Memory, CIC-IDS2017.},
        month = {February},
        }