An Android malware detection system based on machine learning
Description: The Android smartphone, with its open source character
and excellent performance, has attracted many users. However,
the convenience of the Android platform also has motivated
the development of malware. The traditional method which
detects the malware based on the signature is unable to detect
unknown applications. The article proposes a machine learning-based
lightweight system that is capable of identifying malware on Android
devices. In this system we extract features based on the static analysis
and the dynamitic analysis, then a new feature selection approach
based on principle component analysis (PCA) and relief are presented
in the article to decrease the dimensions of the features. After that,
a model will be constructed with support vector machine (SVM) for
classification. Experimental results show that our system provides an
effective method in Android malware detection.