Insecure software detection apparatus and detection method, and storage medium

An insecure software detection method, comprising:

• when a first analysis result indicates that software is not secure, analyzing, by a processor, the software by using a first neural network model, to obtain a second analysis result, wherein the first analysis result is obtained by analyzing the software by using a second neural network model, the second analysis result indicates that the software is not secure, power consumption of the first neural network model is greater than power consumption of the second neural network model, and a computing capability of the first neural network model is greater than a computing capability of the second neural network model;
• and
• performing, by a general-purpose processor, security processing on the software based on the second analysis result.

A computer-readable storage medium, comprising instructions, wherein when the instructions are run on an electronic device including a processor and a general-purpose processor, the electronic device is enabled to perform a method comprising:

• when a first analysis result indicates that software is not secure, analyzing, by the processor, the software by using a first neural network model, to obtain a second analysis result, wherein the first analysis result is obtained by analyzing the software by using a second neural network model, the second analysis result indicates that the software is not secure, power consumption of the first neural network model is greater than power consumption of the second neural network model, and a computing capability of the first neural network model is greater than a computing capability of the second neural network model;
• and
• performing, by the general-purpose processor, security processing on the software based on the second analysis result.