Title: A model for detecting cyber security intrusions using machine learning techniques

Authors: Leo John Baptist; Janani Selvam; Divya Midhun Chakkaravarthy

Addresses: Information Technology, Lincoln University College, Wisma Lincoln, No. 12-18, Jalan SS 6/12, 47301, Petaling Jaya, Selangor Darul Ehsan, Malaysia ' Faculty of Engineering, Lincoln University College, Malaysia ' Faculty of Engineering, Lincoln University College, Malaysia

Abstract: Because hackers are using more sophisticated methods, the number of cyberattacks is rising at an alarming rate. In addition, maintaining adequate levels of cyber security is becoming more difficult on a daily basis due to the prevalence of malicious actors carrying out cyberattacks in the modern digital environment. Therefore, in order to have a safe network, it is required to establish privacy and security measures for the systems. A substantial amount of further research is required in the domain of intrusion detection. This study introduces an intrusion detection tree (referred to as 'IntruDTree'), which is a security model based on machine learning. Ultimately, the efficacy of the IntruDTree model was assessed by the execution of tests on many cybersecurity datasets. To assess the efficacy of the resulting security model, we conduct a comparative analysis between the outputs of the IntruDTree model and those of other well-established machine learning techniques.

Keywords: cybersecurity; cyber-attacks; anomaly detection; intrusion detection system; machine learning; ML.

DOI: 10.1504/IJESDF.2025.148217

International Journal of Electronic Security and Digital Forensics, 2025 Vol.17 No.5, pp.582 - 592

Received: 12 Sep 2023
Accepted: 13 Nov 2023
Published online: 01 Sep 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article