Back-propagation neural network on Markov chains from system call sequences: a new approach for detecting Android malware with system call sequences

摘要: Android has become the most prevalent mobile system, but in meanwhile malware on this platform is widespread. System call sequences are studied to detect malware. However, detection with these approaches relies common system-call-subsequences. It not so efficient because it difficult decide appropriate length of subsequences. To address issue, authors propose a new approach, back-propagation neural network Markov chains from system (BMSCS). treats one sequence as homogeneous stationary chain and applies (BPNN) by comparing transition probabilities chain. Since another significantly different those benign applications, BMSCS can efficiently capturing anomaly state transitions help BPNN. The evaluate performance experiments real application samples. experiment results show that F -score achieves up 0.982773, which higher than other methods literature.