Paper Contents
Abstract
In todays digital landscape, securing computer networks against sophisticated cyberattacks has become increasingly critical. Traditional Intrusion Detection Systems (IDS) often fall short in identifying novel and evolving threats due to their reliance on static rules and known attack signatures. To address these limitations, this research introduces a Machine Learning-based Cyber Intrusion Detection System (CIDS-ML) that enhances detection accuracy and adapts to changing attack patterns. The system follows a structured workflow that includes data collection, preprocessing, feature selection, model training, evaluation, and real-time deployment. Utilizing the KDD Cup 1999 dataset, the system classifies network traffic as either normal or malicious using multiple classification algorithms, including Random Forest, K-Nearest Neighbors, Decision Tree, Support Vector Machine, and Logistic Regression. Real-time monitoring is achieved through a Flask-based web application, whileattack trends and detectionperformance are visualized using web technologies and Matplotlib. The hybrid detection approach integrating both signature-based and anomaly-based techniques demonstrates improved accuracy, scalability, and real-time applicability in modern network environments.
Copyright
Copyright © 2025 Meenaroshini.P. This is an open access article distributed under the Creative Commons Attribution License.
