Copyright © 2025 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{165475,
        author = {M.Swapna and V.B.S Krishna and A.Deepthi and T.Chandan},
        title = {DEEP LEARNING BASED NETWORK INTRUSION DETECTION},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {11},
        number = {1},
        pages = {1104-1111},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=165475},
        abstract = {Network intrusion detection is a pivotal component of cybersecurity, focusing on identifying and mitigating unauthorized access, misuse, or malicious activities within a computer network. As cyber threats grow increasingly sophisticated, the demand for effective intrusion detection mechanisms is paramount to ensure the security and integrity of networked systems. Traditional methods typically utilize a combination of signature-based and anomaly-based approaches, each with its inherent strengths and limitations. However, achieving high detection accuracy while minimizing false positives and adapting to evolving threats remains a significant challenge.
In this research project, we explore the efficacy of advanced machine learning techniques, including Support Vector Machines (SVM), Multilayer Perceptron (MLP), Random Forest, Logistic Regression, Decision Trees, and AdaBoost Classifiers, to enhance network intrusion detection. Through rigorous experimentation, our study reveals that SVM achieves a notable accuracy rate of 94%, effectively distinguishing normal network traffic from various types of attacks. Furthermore, the integration of Convolutional Neural Network (CNN) algorithms bolsters our detection capabilities, attaining an impressive accuracy rate of 95%. Additionally, the implementation of Ensemble Learning Methods, such as the Voting Classifier, further elevates accuracy to an outstanding 98%. This robust performance underscores the potential of ensemble learning in amalgamating predictions from diverse classifiers, significantly enhancing the overall efficacy of intrusion detection systems. Our findings demonstrate that leveraging deep learning and ensemble learning methods can substantially improve the precision and adaptability of network intrusion detection systems, addressing contemporary cybersecurity challenges.
},
        keywords = {Network Intrusion Detection System, Deep Learning, CNN, SVM, Ensemble Learning, Cybersecurity},
        month = {},
        }