Detection technology of malicious code family based on BiLSTM-CNN
Guodong Wang, Tianliang Lu, Haoran Yin · Journal of Physics Conference Series · 2020
Abstract The explosive growth of the number of malicious code makes it one of the important threats to network security. Among them, a new type of malicious code family accounts for a small part, and most of them are generated by mutation on the basis of the original family. Based on batch processing of newly added malicious code, this paper proposes a malicious code family detection technology combining malicious code visualization and deep learning. The malicious code executable file is directly converted into a grayscale image, and then the BiLSTM-CNN deep learning algorithm is used to detect the malicious code family. Experiments prove that the model has higher accuracy.