IoT-Malware Detection Based on Byte Sequences of Executable Files

Abstract

Attacks towards the Internet of Things (IoT) devices are on the rise. To enable precaution and countermeasure against IoT malware, we present a cross-platform analysis of IoT malware programs based on static discriminating information extracted directly from ELF binaries. With experiments on a dataset composed of more than 222K samples cross 7 different CPU architectures, we demonstrate that efficient malware detection can be realized with near optimal accuracy.