Malware detection based on semi-supervised learning with malware visualization

Gao, Tan; Zhao, Liancheng; Li, Xudong; Chen, Wen

doi:10.3934/mbe.2021300

Cited by 6 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To prevent the preset parameter problem, the random search or Gaussian optimization method (19) will be used to determine the optimal values of these parameters in a future study. (9) 93.37 Garcia and Muga II (13) 95.62 Gao et al (14) 97.95 Nataraj et al (15) 97.18 Kalash et al (16) 98.52…”

Section: Discussionmentioning

confidence: 99%

“…The malware family classification performance of the proposed TDLN was evaluated by comparing the classification performance of this network and some other methods for the Malimg data set. (9,(13)(14)(15)(16) The accuracies of the various methods are presented in Table 9. The experimental results indicate that the proposed TDLN has higher accuracy than the other methods.…”

Section: Comparison Of Various Methodsmentioning

confidence: 99%

“…Garcia and Muga II (13) converted a malware binary into an image and used the random forest algorithm to classify various malware families. Gao et al (14) proposed an effective malware classification framework based on malware visualization and semisupervised learning. They used the local binary pattern method for feature extraction and employed a feature fusion method to fuse local and global features, which reduced the time required for feature extraction and improved the relevance of the extracted features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Malware Classification Using a Taguchi-based Deep Learning Network

Lin¹,

Lin²,

Jhang³

2022

Sensors and Materials

View full text Add to dashboard Cite

Malware is designed to damage computer systems, and malicious targets have proliferated recently. This rising use of malware requires an efficient malware detection method. Because new malware is constantly being created and old malware is constantly updated, manually updating a signature database with newly generated malware samples is increasingly challenging. To reduce the cost of feature engineering and the requirement for domain expert knowledge, researchers have used image-sensing methods to solve the malware family classification problem. In this study, a Taguchi-based deep learning network (TDLN) with optimization of the parameter combination is proposed for malware family classification. A total of 36 experiments were conducted and nine influential factors with various levels were selected for determining the optimal parameters of the proposed TDLN. The experimental results indicate that the accuracy, precision, and recall of malware family classification when using the proposed TDLN are 98.71, 96.90, and 96.78%, respectively. Moreover, the accuracy, precision, and recall of the proposed TDLN are 2.03, 5.59, and 6.09% higher, respectively, than those of the original deep learning network for the Malimg data set.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Comparison Of Various Methodsmentioning

confidence: 99%