Workflow of the proposed malware classification method based on FSGCN.

<p>This figure illustrates the process from handling imbalanced datasets using the SMOTE algorithm, constructing directed graphs for API sequences, extracting multi-dimensional attribute features, computing first-order and second-order adjacency matrices, generating feature embeddings with GCN...

Full description

Saved in:

Bibliographic Details
Main Author:	Cuihua Ma (14855149) (author)
Other Authors:	Zhenwan Li (20890032) (author), Haixia Long (556765) (author), Anas Bilal (11785200) (author), Xiaowen Liu (190190) (author)
Published:	2025
Subjects:	Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified smote ), ensuring many existing methods incorporating node attributes convolutional neural network develop advanced models deep learning techniques world malware datasets structural information inherent graph convolutional network structural information network threats malware detection machine learning imbalanced datasets approach models xlink "> typically rely two real synthetic minority sequential nature sequence instructions sampling technique rigorously evaluated results demonstrate introduce first increasingly turning growing complexity grayscale images extensive experiments effectively capture directional relationships directed graph dgcn ). cnn ). classified using approaches consider approach compared
Tags:	Add Tag No Tags, Be the first to tag this record!

Workflow of the proposed malware classification method based on FSGCN.

Similar Items