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{189370,
        author = {Amrutha Holla and Akash Mallappa Bilur and Harsha S and Inchara S and Manohar Nelli V},
        title = {AI Based Network Intrusion Detection system},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {5433-5438},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189370},
        abstract = {The rapid expansion of networked systems and cloud-based services has significantly increased the attack surface of modern digital infrastructures. Conventional intrusion detection mechanisms, which primarily rely on static rules and predefined signatures, are increasingly ineffective against sophisticated and evolving cyber threats. This paper presents a comprehensive AI-based Network Intrusion Detection System (NIDS) that integrates machine learning–driven flow-level analysis with real-time network traffic monitoring. The proposed system employs supervised learning models trained on realistic benchmark datasets, namely CICIDS2017 and CICIDS2018, and deploys the trained model using a lightweight FastAPI-based inference backend. A custom live sensor captures packets from active network interfaces, constructs bidirectional flows, extracts CICFlowMeter-style features, and submits them for real-time classification.},
        keywords = {Network Intrusion Detection, Machine Learning, XGBoost, Cyber Security, Real-Time Monitoring, CICIDS},
        month = {December},
        }