Interruption Identification System Using Machine Learning

Karan Mahesh Gangwani, Utkarsh Mishra, Dr. Sreekumar K, Dr. Sibi Amaran

Abstract: Intrusion Detection Systems (IDS) are essential for safeguarding network infrastructures by continuously monitoring and detecting potential security threats. However, traditional approaches struggle to match the growing sophistication of modern attacks, prompting the need for advanced methodologies. This study presents a machine learning-driven IDS framework utilizing Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) algorithms. The process includes steps such as data collection, preprocessing, feature extraction, model training, and performance assessment. Experimental findings reveal that the proposed system achieves notable accuracy, with SVM and KNN models attaining approximately 97% and 99% accuracy, respectively. These results underscore the promise of machine learning in improving IDS performance and fortifying network security.

Keywords: Intrusion Detection System, Machine Learning, SVM, KNN, Network Security, Cybersecurity, Feature Extraction, Model Training

How to Cite?: Dr. Sibi Amaran, "Interruption Identification System Using Machine Learning", Volume 14 Issue 4, April 2025, International Journal of Science and Research (IJSR), Pages: 1749-1754, https://www.ijsr.net/getabstract.php?paperid=SR25331162834, DOI: https://dx.doi.org/10.21275/SR25331162834