Indian Journal of Science and Technology
Year: 2024, Volume: 17, Issue: 2, Pages: 149-165
Review Article
Saqib Malik1*, Narendra Sharma2
1Research Scholar, Department of Computer Application, Sri Satya Sai University of Technology and Medical Sciences, Sehore, Madhya Pradesh, India
2Associate Professor, Department of Computer Science, Sri Satya Sai University of Technology and Medical Sciences, Sehore, Madhya Pradesh, India
*Corresponding Author
Email: [email protected]
Received Date:21 September 2023, Accepted Date:14 December 2023, Published Date:12 January 2024
Background: It is evaluated that there is 70% to 80% of smartphone users have an Android mobile. Given its trend, a lot of malware strikes on the Android OS. In 2018, the largest number of malware attacks was identified, when there were 10.5 billion such malicious activity detected worldwide. Machine learning has emerged as a promising approach for detecting Android malware, and Ensemble machine learning has been shown to enhance the accuracy of malware detection in other domains. Objectives: In this paper, the systematic literature review were conducted using natural language processing. 30 papers are selected from January 2019 to August 2023 to give a clear picture of the most recent work in Android malware detection using ensemble machine learning. Methods: Initially the ensemble machine learning analysis were categorized in Android malware detection into four groups. Static Ensembles, Dynamic Ensembles, Hybrid Ensembles and Structural Ensembles method and compare the outcomes of empirical evidence with the help of a systematic literature review using the natural language processing method. Findings: The findings demonstrate an emerging trend of using NLP for Android malware detection in combination with ensemble machine learning models. The use of natural language processing (NLP) enhances the capacity to identify harmful patterns by making it easier to extract key features from textual input. The paper also emphasizes the variety of ensemble models used, including Tree-Based, Meta ensemble, Specialized ensemble and others. Significance : The novel aspects of this paper are its extensive comparative evaluation of ensemble and non-ensemble models, its original combination of NLP and ensemble machine learning for Android malware detection, and its extensive review of the literature with an eye toward future directions and research gaps. As a result, based on the present research community, it is important to develop some unique ways to enhance Android malware detection.
Keywords: Ensemble Machine Learning, Static analysis ensemble, Dynamic Analysis Ensembles, Hybrid Feature Ensembles, Structural Analysis Ensembles
© 2024 Malik & Sharma. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)
Subscribe now for latest articles and news.