Ruzaili, Helmy Hanyff Hairudin and Abdul Razak, Azran and Zolkipli, Mohamad Fadli (2024) Study on Machine Learning Implementation in Cybersecurity for Security Defend and Attack. Borneo International Journal (BIJ), 7 (2). pp. 27-40. ISSN 2636-9826

Preview

PDF - Published Version Available under License ["licenses_description_cc4_by_nc_nd" not defined]. Download (146kB) | Preview

Abstract

This comprehensive study explores the utilization of Machine Learning (ML) in the field of cybersecurity, emphasizing its substantial contribution to both defensive and offensive strategies. In contrast to conventional rule-based methodologies, machine learning systems can dynamically adjust to changing threats by acquiring patterns and anomalies from vast datasets. This study investigates the defensive utilization of machine learning (ML) in threat detection, anomaly identification, and security breach prediction. Additionally, it examines the offensive applications of ML, wherein attackers exploit vulnerabilities by applying advanced ML techniques. The study additionally examines the pragmatic implementations of machine learning (ML) in cybersecurity, specifically emphasizing a range of tools such as DeepExploit, Scikit-learn, Metasploit, Nmap, and antivirus software. An assessment is conducted to evaluate the defensive capabilities of Intrusion Detection Systems, firewalls, Security Information and Event Management systems, and email security solutions that utilize Machine Learning. Machine learning in these domains signifies a pivotal advancement in cybersecurity tactics, empowering firms to address cyber risks better

Item Type:	Article
Uncontrolled Keywords:	Machine Learning; Cybersecurity Attack; Cybersecurity Defends
Subjects:	L Education > LB Theory and practice of education
Divisions:	College of Arts and Sciences
Depositing User:	Mdm. Rozana Zakaria
Date Deposited:	06 Apr 2026 12:05
Last Modified:	06 Apr 2026 12:05
URI:	https://repo.uum.edu.my/id/eprint/32798

Actions (login required)

View Item