MAKG: A Mobile Application Knowledge Graph for the Research of Cybersecurity

Large-scale datasets for mobile applications (a.k.a."app") such as AndroZoo++ and AndroVault have become powerful assets for malware detection and channel monitoring. However, these datasets focus on the scale of apps while most apps in them remain isolated and cannot easily be referenced and linked from other apps. To fill these gaps, in this paper, we present a mobile application knowledge graph, namely MAKG, which aims to collect the apps from various resources. We design a lightweight ontology of apps. It can bring a well-defined schema of collected apps so that these apps could share more linkage with each other. Moreover, we evaluate the algorithms of information extraction and knowledge alignment during the process of construction, and select the competent models to enrich the structured triples in MAKG. Finally, we list three use-cases about MAKG that are helpful to provide better services for security analysts and users.