Malware Analysis with Machine Learning for Evaluating the Integrity of Mission Critical Devices

Abstract

The rapid evolution of technology in our society has brought great advantages, but at the same time it has increased cybersecurity threats. At the forefront of these threats is the proliferation of malware from traditional computing platforms to the rapidly expanding Internet-of-things. Our research focuses on the development of a malware detection system that strives for early detection as a means of mitigating the effects of the malware’s execution. The proposed scheme consists of a dual-stage detector providing malware detection for compromised devices in order to mitigate the devices malicious behavior. Furthermore, the framework analyzes task structure features as well as the system calls and memory access patterns made by a process to determine its validity and integrity. The proposed scheme uses all three approaches applying an ensemble technique to detect malware. In our work we evaluate these three malware detection strategies to determine their effectiveness and performance.