TITLE:
An Ensemble Machine Learning Based Algorithm to Enhance Detection of Zero-Day Attacks: A Comparative Review
AUTHORS:
Dominic John Kavoi, Charles Jumaa Katila, Richard Otieno Omollo
KEYWORDS:
Zero-Day Attacks, Machine Learning, Ensemble Algorithms, Cybersecurity, Anomaly Detection, Intrusion Detection Systems (IDS), CAN Bus Dataset, Data Analysis
JOURNAL NAME:
Journal of Information Security,
Vol.16 No.3,
July
23,
2025
ABSTRACT: In the current technological landscape, a lot of risks are present due to the availability of existing and novel kinds of attacks. For these attacks to be countered, systems that identify all the variants without any false positives and false negatives are in high demand. The existence of traditional attack detection methods, such as the signature-based algorithms, has proven that they cannot spot new attacks. This is because they work based on a database that has signatures of attacks. The other methods of detecting attacks that have been explored in this study are the hybrid and machine learning methods for detecting zero-day attacks. In this research, we are coming up with an ensemble set of machine learning algorithms that identify novel and existing attacks in real time from an existing dataset. All of these concepts are mainly based on the Confidentiality, Integrity and Availability (CIA) triad. In order to come up with this, the main method of deployment to be used is the machine learning pipeline. The study has a firm foundation based on theorems such as Bayes and the fundamental principles of computational learning theory. This is composed of stages such as the identification, cleaning, analysis and feature engineering of the data. From there, the ensemble algorithm will be implemented, its accuracy measured and then tuned to improve its efficiency.