Adversarial image generation method, computer device, and computer-readable storage medium

A computer device, comprising a processor, a memory, and a network interface, wherein the processor is coupled with the memory and the network interface, the network interface is configured to provide a data communication function, the memory is configured to store program codes, and the processor is configured to invoke the program codes to:

• generate a reference model according to a target classification model, wherein the reference model is classification-equivalent with the target classification model;
• obtain a target image and generating an original noise for the target image according to the reference model;
• input a first noise and the original noise into an adversarial model and output a second noise corresponding to the first noise when the adversarial model meets a convergence condition, wherein the second noise enhances an information entropy of the original noise;
• and
• generate an enhanced noise image corresponding to the target image according to the second noise and the target image, wherein a classification accuracy of the enhanced noise image in the target classification model is less than a classification accuracy of the target image in the target classification model.

A computer-readable storage medium storing a computer program, the computer program comprising program instructions which, when executed by a processor, cause the processor to:

• generate a reference model according to a target classification model, wherein the reference model is classification-equivalent with the target classification model;
• obtain a target image and generating an original noise for the target image according to the reference model;
• input a first noise and the original noise into an adversarial model and output a second noise corresponding to the first noise when the adversarial model meets a convergence condition, wherein the second noise enhances an information entropy of the original noise;
• and
• generate an enhanced noise image corresponding to the target image according to the second noise and the target image, wherein a classification accuracy of the enhanced noise image in the target classification model is less than a classification accuracy of the target image in the target classification model.