Comparative Analysis of Deep Learning-Based Approaches for Detecting Malwares in Android
Malavika N Prof. Dilna P M · International Journal of Research Publication and Reviews · 2025
The use of smartphones has grown rapidly in recent years.This has led to an increase in their popularity as targets for attackers.The field of malware detection is a never-ending competition between attackers and anti-malware developers.According to the latest report published by the computer security company a new malware can be found in online repositories every 8s.So it is important to protect various devices and networks from the malware attack.The increasing sophistication of mobile threats and the adaptability of ML make it a promising solution for Android malware detection.It requires ongoing research and a robust dataset for model training, making it a challenging but impactful field with significant potential for innovation and security enhancement.The wide range of capabilities offered by smartphones and the rising number of activities carried out by their users, including social networking, online banking, and gaming, has given rise to very serious concerns about device security and personal privacy.Since Android is an open-source platform, it is easy for malware developer to launch their attacks and develop Android malware apps that cause severe harm.The project aims to detect malware using a hybrid model by using various deep learning algorithms so thereby performance can be increased.It also uses attention mechansim, sentimental analysis based on the reviews of the customer.The dataset of the project is taken from the Kaggle.Data Sources of Android apps are collected from app stores and third-party sources.Malware samples are gathered from malware repositories such as VirusShare, AndroZoo, DREBIN Dataset, AMD(Android Malware Dataset)..