“…Several dynamic analysis tools for characterizing Android apps have been published in the literature. The majority of these rely on random-based test input generation using Monkey, for example, AASandbox [11], ANANAS [12], Mobile-Sandbox [13], vetDroid [14], TraceDroid [48], Andrubis [49], Dynalog [8], HADM [50], Maline [51], Glassbox [52], NetworkProfiler [53], Andlatis [54], Hu & Neamtiu [55], and Cai & Ryder [56]. Others such as AppsPlayground [38] used a more intelligent event generation technique, but unlike our paper, did not investigate code coverage capabilities in the context of on performance analysis of machine learning-based malware detection.…”