Capturing the Behavior of Android Malware with MH-100K: A Novel and Multidimensional Dataset

Abstract

The fast pace proliferation of Android malware continues to pose challenges to cybersecurity research. To help reshape the future of malware research, we introduce the MH-100K, a dataset that provides a holistic view through 101,975 APK samples, thousands of diverse features and metadata. We use the VirusTotal API to ensure accurate threat evaluation, combining multiple detection methods for precision. Our findings suggest MH-100K is a valuable resource for providing new insights about the malware landscape’s evolution.