Droid-Sec: Deep Learning in Android Malware Detection

As smart:phones and mobile devices are rapidly becoming indispensable for many network users, mobile malware has become a serious threat in the network security and privacy. Especially on the popular Android platform, many malicious apps are hiding in a large number of normal apps, which makes the malware detection more challenging. In this paper, we propose a ML-based method that utilizes more than 200 features extracted from both static analysis and dynamic analysis of Android app for malv -are detection. The comparison of modeling results demonstrates that the deep learning technique is especially suitable for Android mahvare detection and can achieve a high level of 96% accuracy with real-world Android application sets.