MACHINE LEARNING MODEL FOR PREVENTING CYBER SECURITY ATTACKS

Student: Kingsley Edet Oyombio
Supervisor: Mr Ubokobong Benjamin
HOD: Dr Mfreke Emmanuel Umoh
Department of Computer Science
Basic Medical Sciences
AKWA-IBOM STATE POLYTECHNIC (IEI), IKOT-OSURUA, AKWA IBOM STATE

Abstract

This research work is focused on machine learning model for preventing cyber security Attacks using Digital Centre, Akwa Ibom state polytechnic as a case study. The research work was necessary because of the problems of the existing system which include: frequent occurrence of cyber security attacks, information leakage, emergence of new methods of hacking information in cyber environment and Absence of a machine learning system to help in identification of most common method of cyber-attack in order to prevent it. In view of solving the problems, the objectives of the research work are to utilize machine learning approach to determine security flaws in cyber environment by learning and detection of anomalies in server security logs dataset, to implement a system that identifies pattern of cyber security attacks for effective decision making and to implement a machine learning system that can be used to identify the most frequent cyber security attacks. The study is significant because it will help in identifying strategies for securing cyber environment using machine learning approach, identification of security risk in cyber environment and how to prevent them and discover pattern of cyber security attacks for effective decision making. The design methodology adopted is object oriented analysis and design. The programming language used is Python.

Full-Text Access Notice

In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication. During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.

Request authorisation from the author