Malware detection model training method, device and equipment

Abstract

Embodiments of the present disclosure provide a method, device and equipment for training a malware detection model. The method includes: obtaining a training data set; performing feature analysis on equipment samples in the training data set, including: calculating the proportion of missing values ​​in feature columns corresponding to multiple equipment samples, and calculating the proportion of missing values ​​less than or equal to a preset missing threshold The correlation coefficient between the feature column and the label column corresponding to multiple device samples; perform feature preprocessing on the device samples after feature analysis according to the feature analysis results; use the feature preprocessed device samples to train the preset malware detection model, Get the malware detection model. In this way, the preset malware detection model can be quickly trained using the device samples after feature analysis and feature preprocessing, and a malware detection model with strong detection ability can be obtained, and then based on this model, it can quickly and accurately detect whether the device to be detected is infected malicious software.

Description

technical field [0001] The present disclosure relates to the field of machine learning, and in particular to a training method, device and equipment for a malware detection model. Background technique [0002] The network security industry has been committed to the prevention and control of malware attacks. Attackers can use malware to infect victim devices to destroy the confidentiality and integrity of user and enterprise data resources. At present, traditional solutions usually use signature scanning, searching for broad-spectrum features, and heuristic scanning technologies to detect whether a device is infected with malware. However, traditional solutions need to extract a large number of features before performing detection, and the detection efficiency is low. Contents of the invention [0003] The disclosure provides a malware detection model training method, device and equipment, which can improve the detection efficiency of malware. [0004] In a first aspect, a...

AI Technical Summary

Problems solved by technology

At present, traditional solutions usually use signature scanning, searching for broad-spectrum features, and heuristic scanning technologies to detect whether a device is infected with malware. However, traditional solutions need to extract a large number of features before performing detection, and the detection efficiency is low.

Images