Lightweight and Efficient Android Malware Detection Using Manifest File Analysis

Machine learning-based processes have appeared as a favourable redress to descend the intricacy and originality of growing Android menaces. These approaches classify the unknown behaviour of apps as malicious or normal using information about current patterns of malware activities. A manifest file is an essential component of applications that stores metadata about application resources, configurations, and dependencies. Machine learning techniques have played a crucial role in analyzing manifest files and identifying malware. This work explores the substance of manifest file analysis and focuses on its role in identifying disclosure. Additionally, the work examines a collection of 2000 Android app manifest files to recognize components of the manifest for malicious and benign behaviour. Feature extraction techniques are employed to identify manifest files' key particulars, including permissions, hardware requirements, and intent filters, which are potential indicators of malicious actions. The findings demonstrate the value of manifest file analysis as a lightweight and effective method for detecting malware.