Paper Contents
Abstract
The rapid proliferation of Android devices has led to an increase in the development and deployment of malicious applications (malware) targeting the platform. Traditional methods of malware detection, which rely heavily on signature-based techniques, have become less effective due to the evolving nature of malware. This necessitates the development of automated, intelligent systems capable of identifying malware in real- time, with high accuracy and minimal human intervention. This paper explores the landscape of automated Android malware detection, emphasizing the integration of machine learning (ML) and deep learning (DL) techniques. By analyzing large datasets of both benign and malicious applications, these models can identify patterns and anomalies that signify malware. Features such as API calls, permissions, and network traffic are often used to train these models, enabling them to detect even previously unknown malware variantsKey words: Malicious APK, Total Virus, Streamlit, Plotly.
Copyright
Copyright © 2024 Malipatel Abhishek. This is an open access article distributed under the Creative Commons Attribution License.
