A Malware Classification Method Based on the Multi-Layer Feature Fusion of Malware Image Representations and Opcode Markov Images

As the threat of malware to information security becomes increasingly severe, the study of efficient malware classification methods has become more urgent. This paper proposes a multilayer malware classification method based on the fusion of image representation and opcode features. By integrating the features of image-based malware representation and opcode Markov image, the classification performance is enhanced. Specifically, our model introduces two feature fusion modules: a cross-attention-based fusion module and a multiplication-based low-level feature fusion module. These modules achieve effective fusion of deep features, thereby improving the accuracy of malware classification. Experimental results show that the model combining malware image features extracted by ResNet18 and malware opcode Markov image features extracted by EfficientNetB0 performs the best. Comparative experiments with traditional feature fusion methods demonstrate that our approach has significant advantages in classification performance. Further experiments on another dataset validate the generalization ability of our method. This research provides an efficient and effective solution for malware classification.

Name dc:type.qualificationname

msc

Level dc:type.qualificationlevel

masters

Grantor dc:publisher.institution

University of Wales Trinity Saint David

Year dc:date.issued

2024

Author dc:creator

• Xu, Jinwei

• TK Peirianneg drydanol. Peirianneg Niwclear Electronig

Dc Identifier Grantnumber

UWTSD

OAI identifier oai:identifier

oai:repository.uwtsd.ac.uk:3309