In this project, we aim to systematize the knowledge base about existing mobile malware (especially on Android) and quantify their threats so that we can develop principled solutions to provably determine their presence or absence in existing marketplaces. The hypothesis is that there exist certain fundamental commonalities among existing mobile malware. Accordingly, we propose a mobile malware genome project called MalGenome with a large collection of mobile malware samples.  Based on the collection, we can then precisely systematize their fundamental commonalities (in terms of violated security properties and behaviors) and quantify their possible threats on mobile devices.  After that, we can develop principled solutions to scalably and accurately determine their presence in existing marketplaces. Moreover, to predict or uncover unknown (or zero-day) malware, we can also leverage the systematized knowledge base to generate an empirical prediction model. This model can also be rigorously and thoroughly evaluated for its repeatability and accuracy.

TEAM

PI: Xuxian Jiang
Student: Yajin Zhou