A static Android malicious code detection method based on multi-source fusion

摘要: The rapid development of mobile malwares makes the traditional signature-based and single-feature based malware detection methods a challenging task. surge new with more complex structures dynamic characteristics leads to efficient fusion multi-source malicious information difficult in detection. In this paper, we propose method detect Android by emphasizing on static features, control flow graph, repacking characteristics. Each category features is treated as an independent source feature extracting rules building classification. Then, Dempster-Shafer algorithm used fuse these sources. This can improve accuracy without adding too many instability that are extracted from disassembled codes, have better performance resistance code obfuscation technologies. To verify our method, different categories apps collected build dataset experiment. Based dataset, achieve 97% 1.9% false positive rate. Copyright © 2015John Wiley & Sons, Ltd.