|
AUTHOR(S): Bartholomew Idoko, Franscisca Ogwueleka, Steven Bassey
|
TITLE |
 PDF |
ABSTRACT The inability of the traditional malware detection systems to accurately detect and classify instances of malware attacks has become a problem that requires in-depth research. Consequently, Machine Learning (ML) based malware detection system could be a better tool to achieve the expected objectives. This study is a systematic review of malware analysis and detection in four (4) different citation databases and considers the total of 262 research articles published from 2014 to 2024. The methodology adopted in the study include evaluation and validation, search strategy, inclusion and exclusion criteria, selection procedure, and data extraction from the selected articles. The aim of the study is to analyze the papers published in the four citation databases based on Machine learning tasks (regression or classification), research methodology and ML algorithms used by the different authors. The results were presented as classification or regression functions and validated using bar charts and pie charts. The common objectives and anomaly in the detection scenarios were analyzed and gaps identified. The study will serve as a guide to researchers for decision making with regards to developing the best ML algorithm that could solve malware detection problems. |
KEYWORDS Malware, detection; malware, analysis; Machine Learning; accuracy; model; classification |
|
Cite this paper Bartholomew Idoko, Franscisca Ogwueleka, Steven Bassey. (2025) Systematic Literature Review on Malware Detection and Machine Learning Algorithms: Identifying Gaps for possible Remedies.. International Journal of Computers, 10, 179-189 |
|
