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{166810,
        author = {Kapilavai Pravallika and Kapilavai Pravallika and Dr.M.Dhanalakshmi},
        title = {Dynamic Web Application for Real Time Threat Detection using ML algorithms},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {2},
        pages = {2043-2051},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=166810},
        abstract = {In today's highly interconnected world, the security of computer networks is paramount. Conventional systems have difficulty identifying new attacks and frequently produce a significant number of false positives. In this project the real-time threat detection and classification is done by using Categorical Boosting (CatBoost), k-medoids clustering and Deep Q Networking (DQN) algorithms. Later, dynamic web application is build on top of CatBoost algorithm that helps the user to enter a string value that has the details about the network packet and help to classify it as normal or malicious attack type.  The time complexity for the algorithms is comparatively higher than other supervised algorithms but these algorithms are good for outlier analysis. The CatBoost algorithm gave an accuracy of 99.24% for the multi-class classification and other algorithms gave a decent accuracy score when combining them with supervised model for the binary and multi-class classification.},
        keywords = {Network Intrusions, Network intrusion detection, Categorical Boosting, K-Medoids, Deep Q Network, Streamlit API, Normal, DoS, R2L, U2R, Probe, Anomaly.},
        month = {July},
        }