Hongliang Liang, Yilun Xie and Yan Song, Beijing University of Posts and Telecommunications, China

iOS is a popular operating system on Apple’s smartphones, and recent security events have shown the possibility of stealing the users' privacy in iOS without being detected, such as XcodeGhost. So, we present the design and implementation of a malware vetting system, called DMIA. DMIA first collects runtime information of an app and then distinguish between malicious and normal apps by a novel machine learning model. We evaluated DMIA with 1000 apps from the official App Store. The results of experiments show that DMIA is effective in detecting malwares aimed to steal privacy.

iOS, Malware Detection, Dynamic Analysis, Machine Learning