REMSF: A Robust Ensemble Model of Malware Detection Based on Semantic Feature Fusion

With the rapid development of Internet of things, the amount and distribution of malware has greatly increased. Internet of things platform needs new defense technologies to protect users from new the increasing number and complexity of malware. This paper extracts import Dlls and import APIs from original PE file, and uses heterogeneous graph to describe higher-level semantic relationship between two PE files. Besides this we construct four static features to comprehensively describe PE file. Based on ensemble learning we develop a model called REMSF which fuses five features mentioned above. To evaluate REMSF, we collect 5370 executable PE files from real world for series of experiments, in which REMSFs detection accuracy can reach 99.07%.