Digital image watermarking method based on adversarial attack

Abstract

The invention discloses an image watermarking method based on adversarial attack. The method comprises the following specific steps: (1) establishing a neural network; (2) generating a training set; (3) training a neural network; (4) partitioning the carrier image into blocks; (5) dividing and converting the watermark sequence; (6) generating an adversarial image block by using the adversarial attack to obtain a watermark-containing image; (7) partitioning the image containing the watermark; (8) obtaining a watermark sequence fragment by using a neural network; and (9) splicing the watermark sequence fragments to obtain the watermark sequence. The method has the advantages that on the premise that indexes such as imperceptibility and safety of a watermark algorithm are met, the performance such as embedding capacity can be enhanced along with improvement of the classification capacity of a network model, and meanwhile the algorithm has good robustness to attacks such as filtering attacks, clipping and compression.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a digital image watermarking method based on an adversarial attack in the technical field of information hiding. The present invention can be used for information hiding in the process of digital image dissemination, and can embed watermark information into images in a manner imperceptible to human vision. In scenarios such as copyright disputes, the watermark information can be extracted through the extraction process to realize copyright protection and identity certified. Background technique [0002] Watermark technology is an important technology to solve security issues such as copyright disputes. In recent years, with the popularity of digital multimedia, especially digital images, various attack methods against digital images have brought new challenges to image watermarking technology and put forward higher requirements. Image watermarking technology is b...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide an image watermarking method based on adversarial attacks to solve the problems of poor watermark invisibility and weak watermark robustness in watermarked images, and at the same time solve the shortcomings of the above existing technologies. The problem of low watermark embedding capacity caused by carrier image limitation

Images