An Improved Image Steganography Framework Based on Y Channel Information for Neural Style Transfer

Abstract

Neural style transfer has effectively assisted artistic design in recent years, but it has also accelerated the tampering, synthesis, and dissemination of a large number of digital image resources without permission, resulting in a large number of copyright disputes. Image steganography can hide secret information in cover images to realize copyright protection, but the existing methods have poor robustness, which is hard to extract the original secret information from stylized steganographic (stego) images. To solve the above problem, we propose an improved image steganography framework for neural style transfer based on Y channel information and a novel structural loss, composed of an encoder, a style transfer network, and a decoder. By introducing a structural loss to restrain the process of network training, the encoder can embed the gray-scale secret image into Y channel of the cover image and then generate steganographic image, while the decoder can directly extract the above secret image from a stylized stego image output by the style transfer network. The experimental results demonstrate that the proposed method can effectively recover the original secret information from the stylized stego image, and the PSNR of the extracted secret image and the original secret image can reach 23.4 and 27.29 for the gray-scale secret image and binary image with the size of 256×256, respectively, maintaining most of the details and semantics. Therefore, the proposed method can not only preserve most of the secret information embedded in a stego image during the stylization process, but also help to further hide secret information and avoid steganographic attacks to a certain extent due to the stylization of a stego image, thus protecting secret information like copyright.

An image steganography using improved hyper-chaotic Henon map and fractal Tromino

“…Let 𝐻𝑝 described the amount of pixels has 𝑗𝑗 gray levels in the 𝑖𝑖 𝑡ℎ plain image and 𝐻𝑒 described the amount of 𝑖𝑖, 𝑗𝑗 𝑖𝑖, 𝑗𝑗 pixels has 𝑗𝑗 gray levels in the 𝑖𝑖 𝑡ℎ encrypted image. Then, it gives the results as 𝑗𝑗 = (0, 1, 2, 3, … 255) and 𝑖𝑖 = (1, 2, 3) in the encryption efficiency of a color image can be explained in (19).…”

“…However, the information will not be changed since changing the single value elements directly will affect the image's lighting. Lin et al [19] created a steganography structure for neural style transmission by presenting the Y channel data to avoid steganographic attacks. However, the planned Y-channel still requires a big space for optimization.…”

Hiding Image within Image Based on Deep Learning

“…Subsequently, Bi et al [24] proposed an ISTNet scheme to hide a grayscale image into a stylized image during style migration, and the generated secret-containing image is indistinguishable from the artistic image on the Internet, as shown in figure 7. An improved image steganography framework based on Y-channel neural style migration was proposed by Lin et al [25], integrating Y-channel embedding initially and style change of the image after that. The secret image's content was concealed in the middle of the cover image using the NST approach, according to Mallika et al Utilizing the middle-hidden style characteristic of the cover picture, the secret image is created by using the NST approach to conceal its content.…”

Hide text in an image using Blowfish algorithm and development of least significant bit technique

“…For normal usage or transmission, the cover image holding secret information is referred to as a steganographic (stego) image, and it has a similar visual effect to the original cover image, this affects the cover image's application scene. Most traditional methods superimpose secret information directly on a specific pixel in the image, which can harm the original image significantly [5]. Text, picture, audio, and video steganography are types diverse used in steganography [6].…”