File virus detection method and device

Abstract

The invention discloses a virus detection method and apparatus for a file. A specific embodiment of the method comprises the steps of extracting characteristic information from a to-be-detected file, wherein the characteristic information is used for representing a running behavior of the to-be-detected file; performing normalization processing on the characteristic information to obtain normalized data corresponding to the characteristic information; and converting the normalized data into binary data, and importing the binary data into a pre-trained virus detection model to perform virus detection to obtain a virus detection result. According to the implementation mode, a virus identification deviation caused by quantity can be avoided, the virus identification accuracy can be improved, and the virus identification speed is increased.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to the technical field of virus detection and processing, and in particular to a file virus detection method and device. Background technique [0002] The concept of deep learning originated from the study of artificial neural networks. A multi-layer perceptron with multiple hidden layers is a deep learning structure. Deep learning combines low-level features to form more abstract high-level representation attribute categories or features to discover distributed feature representations of data. The combination of deep learning and neural network is used for virus detection of files, which can accurately identify virus files. [0003] The existing virus detection method combined with deep learning and neural network still has shortcomings. For example, the existing virus detection method combined with deep learning and neural network has limited sample data when t...

AI Technical Summary

Problems solved by technology

[0003] The existing virus detection method combined with deep learning and neural network still has shortcomings. For example, the existing virus detection method combined with deep learning and neural network has limited sample data when training the virus detection model, which directly leads to The virus detection model can only detect a small amount of viruses based on the sample data, and cannot take advantage of the deep learning neural network; at the same time, the existing deep learning neural network is not optimized for specific virus characteristics, resulting in the detection of the virus detection model. Viruses are not accurate

Images