An Android malware detection system based on machine learning

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