Malware Detection in Smartphone Using Hidden Markov Model

In recent years, smart phone technology is becoming increasingly popular. The dangers of mobile phone malwares are becoming more and more serious. In this paper we present a new mobile smartphone malware detection scheme based on Hidden Markov Model (HMM) which is different from the traditional signature scanning methods. Firstly, we monitor the key press and system function call sequence, and take the key press as hidden state. After decoding HMM model, abnormal process can be detected using the matching rate of HMM output to the actual key press sequence. The experimental results demonstrate that the proposed method can effectively detect mobile malwares.