SCREDENT: Scalable Real-time Anomalies Detection and Notification of Targeted Malware in Mobile Devices

摘要: Abstract The ubiquitous availability of Android devices has led to increasing malicious mobile attacks targeting the operating system. In recent times, adversaries leverage situational awareness, user and device context create targeted malware for devices. Several security tools such as Mobile Sandbox, TargetDroid, ANANAS focus on tailoring detection schemes individual users suffer from scalability by analyzing user's activities. To best our knowledge, these do not incorporate group profiling in their automated user-behavior driven dynamic analysis. addition, adaptive location-based alerts are provided users. We propose SCREDENT: Scalable Real-time Anomalies Detection Notification Targeted Malware Devices, provide a scalable system classify, detect, predict real-time. SCREDENT incorporates behavior-triggering probabilistic models grouping minimize number parallel analysis instances needed. leverages container technology perform allow modularity emulation improves. uses adaptive, notification principles geographical fence which warn attacks. Finally, provides proactive, if at least one members triggered activities an application currently used individual.