Android Malware Characterization using Metadata and Machine Learning Techniques

摘要: Android Malware has emerged as a consequence of the increasing popularity smartphones and tablets. While most previous work focuses on inherent characteristics apps to detect malware, this study analyses indirect features meta-data identify patterns in malware applications. Our experiments show that: (1) permissions used by an application offer only moderate performance results; (2) other publicly available at Markets are more relevant detecting such developer certificate issuer, (3) compact efficient classifiers can be constructed for early detection applications prior code inspection or sandboxing.