DroidAPIMiner: Mining API-Level Features for Robust Malware Detection in Android

摘要: The increasing popularity of Android apps makes them the target malware authors. To defend against this severe increase malwares and help users make a better evaluation at install time, several approaches have been proposed. However, most these solutions suffer from some shortcomings; computationally expensive, not general or robust enough. In paper, we aim to mitigate installation through providing lightweight classifiers. We conducted thorough analysis extract relevant features behavior captured API level, evaluated different classifiers using generated feature set. Our results show that are able achieve an accuracy as high 99% false positive rate low 2.2% KNN classifier.