Details

Autor(en) / Beteiligte

• Chen, Jinrong
• Jia, Xiaoqi
• Zhao, Chongming
• Zhang, Weijuan
• Huang, Qingjia

Titel

Using the Rgb Image of Machine Code to Classify the Malware

Ist Teil von

• 2020 IEEE 5th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA), 2020, p.542-549

Ort / Verlag

IEEE

Erscheinungsjahr

2020

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• Aiming at the problem of high complexity caused by the excessive dependence of feature set on expert experience and high feature dimension in current malware classification methods, this paper proposes a classification method that is based on rgb image of assembly instructions and Convolutional Neural Network (CNN). This paper firstly gets the assembly code file of the executable malware sample, then generates rgb pixels by analyzing machine codes for each kind of assembly instructions (such as mov and add), then generates rgb images through these rgb pixels. Finally, the classification model is trained on the training sample set by using CNN. We have carried out a series of experiments, and through these experiments, it is proved that our method can be got a good result in malware classification.