Dynamic malicious code detection technology based on deep learning
Author
Abstract

In this paper, the malicious code is run in the sandbox in a safe and controllable environment, the API sequence is deduplicated by the idea of the longest common subsequence, and the CNN and Bi-LSTM are integrated to process and analyze the API sequence. Compared with the method, the method using deep learning can have higher accuracy and work efficiency.

Year of Publication
2022
Conference Name
2022 20th International Conference on Optical Communications and Networks (ICOCN)
Google Scholar | BibTeX