Normal behavior neural network model training method, system and device and storage medium

Abstract

The invention relates to a normal behavior neural network model training method, system and device and a storage medium, and relates to the field of neural network model training, and the method comprises the steps: obtaining behavior data and the source information of the behavior data; obtaining a data transmission environment of corresponding behavior data based on the source information; judging whether the behavior data can be regarded as training data or not based on the data transmission environment of the behavior data; and after the behavior data is regarded as training data, the training data and the non-abnormal behavior result are transmitted to the normal behavior neural network model, and the normal behavior neural network model is trained. And before the normal behavior neural network model is trained by using the behavior data, judging whether the behavior data is normal data, and if so, using the behavior data. The method has the advantages that the training precision of the normal behavior neural network model can be conveniently improved, and therefore the accuracy of the analysis result can be improved when the normal behavior neural network model is actually used.

Description

technical field [0001] The invention relates to the field of neural network model training, in particular to a normal behavior neural network model training method, system, device and storage medium. Background technique [0002] In order to improve the security of Internet applications, in addition to setting up defense modules such as firewalls and honeypots, some users will also train network intrusion neural network models for real-time detection of uplink and downlink data. Once attack data enters the system, the network intrusion neural network The network model will output analysis results for the attack data, showing that the transmitted data is attack data, so as to improve the security of the system. However, for relatively important systems, in addition to configuring the network intrusion neural network model, a normal behavior neural network model will also be set to detect whether there is anomaly in the normal behavior data to further improve system security. ...

AI Technical Summary

Problems solved by technology

[0004] Regarding the related technologies mentioned above, the inventor believes that real devices are easy to receive attack data. When training the normal behavior neural network model, if the attack data received by the real device is regarded as normal behavior data and transmitted to the normal behavior neural network model, the Training the normal behavior neural network model will affect the training accuracy of the normal behavior neural network model, and it is easy to reduce the accuracy of the output analysis results of the normal behavior neural network model in actual use

Images