CasKDNet:A Malware Classification Method Based on Improved DenseNet
LIU Qiang
WANG Jian
LU Yanli
WANG Yifei
Abstract：In existing malware visualization classification models,there are inadequate accuracy and ro-bustness.For this reason,this paper proposes a malicious code visualization classification method CasKD-Net(Cascade DenseNet with KAN)based on an improved DenseNet.The CasKDNet is to realize the im-provements in accuracy and robustness by three key technologies.Firstly,a cascaded classifier structure is constructed to enhance the feature discrimination ability of texture similar families.Secondly,the KAN structure is used to replace the multi-layer perceptron in the DenseNet network,optimizing the non-linear expression ability of the feature extraction process and improving the overall accuracy of the model.Final-ly,the FFM image restoration algorithm is used to enhance the training set and improve the robustness of the model.It appears from the experimental results on the malicious code dataset Malimg that the CasKD-Net model achieves 99.69％of classification accuracy,and is superior to the existing research methods.Furthermore,in the context of white box attacks,the success rate of FGSM and I-FGSM algorithms at-tack against the CasKDNet only serves as 12.7％and 37.5％respectively,and the model is valid in pre-venting adversarial attacks.
Keywords：malwarecascade classifierKANFFM algorithmadversarial attack
Publication Date：2025-08-30
Online Publishing Date：2025-08-21(First online date of this platform, not the publication date of the document)
Pages：10( 110-119 )