The rapid increase in cyberattacks poses a significant threat to digital infrastructure, highlighting the need for intelligent and timely threat detection systems. This paper presents a machine learning-based approach for classifying cybersecurity threats using network traffic data. Various supervised learning models, including Logistic Regression, Random Forest, Support Vector Machine (SVM), and XGBoost, are applied and evaluated for their performance in detecting and categorizing network-based attacks. The system processes key features such as packet length, port usage, and protocol behavior to identify malicious patterns and determine attack types. A user-friendly interface is developed using Streamlit to support data upload, preprocessing, prediction, and visualization. Experimental results demonstrate that the proposed models, particularly ensemble methods, provide high accuracy in threat classification, offering an effective and scalable solution for proactive cybersecurity defense.
R. Sankar (Wed,) studied this question.