Development of Visualization System Analysis and Network Traffic Pattern to Detect Anomalies and Potential Security Threats

Student: Abdulrahman Abdullahi Aliyu (Project, 2025)
Department of Computer Science and Information Technology
Federal University, Dutsin-Ma, Katsina State

Abstract

ABSTRACT
This project presents a machine learning-based system for detecting anomalies in network traffic. Using unsupervised learning techniques, particularly Isolation Forest, the system analyzes traffic patterns, identifies deviations from normal behavior, and visualizes the findings. The approach enhances early detection of potential threats and supports network security monitoring. traffic has become essential to ensuring the integrity, confidentiality, and availability of digital infrastructure. Traditional detection systems, which often rely on signature-based or supervised learning techniques, fall short in identifying zero-day attacks and previously unknown threats. This project proposes the development of a visualization-driven network anomaly detection system that utilizes unsupervised learning techniques to detect suspicious patterns and activities within network traffic.

Keywords
development visualization system analysis network traffic pattern detect anomalies potential
Filters
Institutions