Malware Detection for E-Commerce Applications using Machine Learning

In order to detect malware in e-commerce apps, this research suggests an automated testing approach that makes use of machine learning techniques. The proliferation of Androidbased e-commerce platforms has led to a rise in malware threats targeting these platforms. We provide a solution to this issue by applying Artificial Neural Network (ANN) and Support Vector Machine (SVM) techniques to accurately categories APK files as malicious or benign. The framework is based on a vast array of Android applications that were carefully chosen to include samples from various e-commerce platforms. Metrics are taken into consideration when training and evaluating the SVM and ANN models using this dataset. F1-score, recall, accuracy, and precision, for example. Users can engage with the detection findings and sign up or sign in using an intuitive web interface built into the system. Our results confirm the efficacy of the proposed architecture, as both the SVM and ANN models classify APK files with high levels of accuracy. Furthermore, the system provides thorough insights into the classification performance through confusion matrices and classification reports. Overall, this work improves the area of malware identification in e-commerce apps and provides a helpful tool for enhancing cybersecurity in the mobile commerce arena.