Received 22 October 2023, accepted 6 November 2023, date of publication 9 November 2023, date of current version 17 November 2023. Digital Object Identifier 10.1109/ACCESS.2023.3331739 Detection of Android Malware Using Machine Learning and Siamese Shot Learning Technique for Security FAHDAH A. ALMARSHAD 1 , MOHAMMED ZAKARIAH 2 , (Member, IEEE), GHADA ABDALAZIZ GASHGARI 3 , EMAN ABDULLAH ALDAKHEEL 4 , AND ABDULLAH I. A. ALZAHRANI 5 1 Department of Information Systems, College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, Al-Kharj 11942, Saudi Arabia 2 Department of Computer Science, College of Computer and Information Science, King Saud University, Riyadh 11633, Saudi Arabia 3 Department of Cybersecurity, College of Computer Science and Engineering, University of Jeddah, Jeddah 23445, Saudi Arabia 4 Department of Computer Science, College of Computer and Information Science, Princess Nourah bint Abdulrahman University, Riyadh 11671, Saudi Arabia 5 Department of Computer Science, College of Science and Humanities-Al Quwaiiyah, Shaqra University, Shaqra 11961, Saudi Arabia Corresponding author: Eman Abdullah Aldakheel (eaaldakheel@pnu.edu.sa) This work was supported by Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia, through Researchers Supporting, under Project PNURSP2023R409. ABSTRACT Android malware security tools that can swiftly identify and categorize various malware classes to create rapid response strategies have been trendy in recent years. Although many application felds have demonstrated the usefulness of implementing Machine Learning and deep learning methods to provide automation and self-learning services, the scarcity of data for malware samples has been cited as a hurdle in creating effcient deep learning-based solutions. In this paper, a one-shot learning-based Siamese neural network is proposed to overcome this issue, as it can both identify malware assaults and categorize malware into multiple categories. The Drebin dataset, which is divided into benign and harmful components, is used in our suggested methodology. The effciency of the suggested strategy is evaluated through a dataset made up of 9476 goodware applications and 5560 Android malware apps. The fve critical phases of its implementation are pre-processing, data partitioning, model architecture, training, and assessment. In both the training and testing phases, Siamese networks are trained to rank sample similarity, and the accuracy is determined using N-way one-shot tasks. According to the experiment’s fndings, our Siamese Shot model fared better than the other standard approaches, obtaining an accuracy of 98.9%. Additionally, the most well-liked platforms are Keras and TensorFlow. INDEX TERMS Android malware, security tools, machine learning, deep learning, one-shot learning, Siamese neural network, Drebin dataset, effciency, N-way one-shot tasks, TensorFlow. I. INTRODUCTION The ‘easy to use’ feature and the effectiveness of various apps, as well as the ongoing improvements in smart devices’ hardware and software, are driving a rapid increase in smart- phone usage and related applications in this technological era [1]. Studies conducted in this feld indicate that by 2024, 4.5 billion people are anticipated to own smartphones [2]. Among these smartphone devices, the most popular smart- phone operating system is Android [3]. A 75.5% market The associate editor coordinating the review of this manuscript and approving it for publication was Barbara Masucci . share is held by Android [4]. As a result of its widespread adoption, Android is more vulnerable to malware and viruses which makes it an appealing target for attackers. However, studies indicate that these threats and assaults can be tackled using Machine learning (ML) as ML algorithms can create a classifer from a set of training instances [5], [6]. Thus, utiliz- ing examples while developing malware detectors avoids the need to specify identifers explicitly. Moreover, Machine learning-based malware detection studies are becoming increasingly common to achieve a high degree of detection accuracy [7], [8]. ML algorithms, which can make decisions after learning from data templates, have VOLUME 11, 2023  2023 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ 127697