Apparatus for detecting a variant malicious code based on neural network learning, method for the same, and computer-readable recording medium on which a program for executing the method is recorded

摘要

The present invention relates to an apparatus for detecting a variant malicious code based on neural network learning, a method therefor, and a computer-readable recording medium on which a program for executing the method is recorded. According to the present invention, since one-dimensional binary data is converted into two-dimensional data without extracting another feature and deep learning is performed via a neural network having a multilayered non-linear structure, malignancy is caused by execution of deep learning. Extract the characteristics of the code and its variants. Therefore, it does not require another feature extraction tool or expert human effort, so analysis time is shortened and variant malignant codes that cannot be detected by existing malignant code classification tools can be detected by deep learning. it can. [Selection] Figure 2