Semantic-based Malware Behavior Description: Past and Future

Abstract

Traditional malware detection is faced with problems of low efficiency and high cost. In recent years, in order to improve the efficiency and accuracy of malware detection, a method based on semantic malware behavior description has been widely studied. In this paper, we firstly classified the current methods of semantic-based malware behavior description by their evolution and characteristics. Secondly, we performed a statistical analysis for the typical description in different aspects. Finally, through statistical analysis, we revealed the challenges faced by semantic-based malware behavior description and its future development prospects.