Android malware family classification based on resource consumption over time

Abstract

The vast majority of today's mobile malware targets Android devices. This has pushed the research effort in Android malware analysis in the last years. An important task of malware analysis is the classification of malware samples into known families. Static malware analysis is known to fall short against techniques that change static characteristics of the malware (e.g. code obfuscation), while dynamic analysis has proven effective against such techniques. To the best of our knowledge, the most notable work on Android malware family classification purely based on dynamic analysis is DroidScribe. With respect to DroidScribe, our approach is easier to reproduce. Our methodology only employs publicly available tools, does not require any modification to the emulated environment or Android OS, and can collect data from physical devices. The latter is a key factor, since modern mobile malware can detect the emulated environment and hide their malicious behavior. Our approach relies on resource consumption metrics available from the proc file system. Features are extracted through detrended fluctuation analysis and correlation. Finally, a SVM is employed to classify malware into families. We provide an experimental evaluation on malware samples from the Drebin dataset, where we obtain a classification accuracy of 82%, proving that our methodology achieves an accuracy comparable to that of DroidScribe. Furthermore, we make the software we developed publicly available, to ease the reproducibility of our results.

Machine learning-based dynamic analysis of Android apps with improved code coverage

“…Other systems include Droidcat [60], STREAM [61], Mobile-Sandbox (2014) [62], Dysign [63], Massarelli et. al [64], Alzaylaee et. al.…”

A Review of Android Malware Detection Approaches Based on Machine Learning

“…The study described in Ref. [143] evaluates whether the application is malicious according to the resource consumption of the application at runtime, focusing on the consumption of CPU, memory, network, and other resources. Researchers in Ref.…”

“…[3], [88], [100]- [103], [105], [107]- [109], [113]- [117], [119], [121], [136], [137], [139], [140], [143], [147], [151]- [153], [155], [157], [162], [166], [167], [169], [175]- [177], [179]- [181], [183], [187], [189], [190], [192], [193], [195], [202], [207], [212]- [216] K-Nearest Neighbors (KNN)…”

MalFamAware: automatic family identification and malware classification through online clustering

“…There exist several approaches for automatic malware classification that are based on classifiers trained with a fixed ground truth of families [3,4]. Although they are highly accurate, they fail in family identification as they can not recognize new families unless they are frequently re-trained on an updated and reliable ground truth, which is commonly not available.…”