Detection of Android Malware Using Machine Learning and Siamese Shot Learning Technique for Security

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 fields 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 efficient 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 efficiency of the suggested strategy is evaluated through a database dataset made up of 9476 goodware applications and 5560 Android malware apps. The five 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 findings, our Siamese Shot model fared better than the other standard approaches, obtaining an accuracy of 98.9%. Additionally, the most wellliked platforms are Keras and TensorFlow.