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{175077,
        author = {S. Kasthuri and Dr. M. Balamurugan and A. Loganayaki},
        title = {Defensive Strategy for Epidemic Cyber Security threat Modelling and Analysis Using Support Vector Machines},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {1961-1967},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175077},
        abstract = {Digital systems, networks, and data require vital domain protection against malicious intrusion and unauthorized access through cybersecurity measures. Epidemic cyber threats like rapid malware and ransomware, and botnets threaten the domain because they exploit system vulnerabilities while spreading between connected networks. Today's Security threat models depend mainly on signature-based methods with heuristic detection methods, yet struggle to detect new attacks because they require defined rule sets and attack signatures. The traditional methods experience both computational inefficiency and numerous incorrect identifications that reduce their capability to stop security threats when they occur in real time. A defensive strategy for epidemic cyber threat modelling and analysis with Support Vector Machines (SVM) serves as the main proposal in this paper to address existing challenges. The model starts with feature value normalization through Min-Max scaling before model convergence optimization. The next step incorporates Recursive Feature Elimination (RFE) to choose essential features that boost classification results and diminish computing requirements. We employ SVM for classification because this method works well with large datasets while properly identifying benign from malicious computer operations. Our proposed method shows experimental result of increasing threat detection accuracy through built-in false positive rate which establishes it as a strong solution for contemporary cybersecurity protection.},
        keywords = {cybersecurity, malicious, threat, Min-max scaling, RFE, SVM, benign},
        month = {April},
        }