Deep learning model with sequential features for malware classification

HIGHLIGHTS

SUMMARY

Messay-Kebede et_al proposed a detection model using both traditional machine_learning methods and autoencoder-based methods. A few classes were identified by the traditional machine_learning model, and others were classified with autoencoders. Gibert et_al extracted byte and opcode sequences, which were fed into a classifier composed of two convolutional neural_networks (CNNs). Barath et_al used a CNN-LSTM approach for feature extraction and two types of machine_learning for classification using support vector machines and logistic regression. Researchers Ahmadi M and Zhang Y et_al extracted 15 and 6 features from malware, respectively, with more comprehensive information . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or Email

Password

Remember me

Lost your password?

If you don't have an account, you can create one here.