Image steganography based on style transfer and quaternion exponent moments

Abstract

Although the existing steganography methods can successfully embed secret information into the carrier image without introducing distortion into the appearance of the carrier image, the difference in distribution between the carrier image and stego image still cannot resist the detection by statistics-based steganalysis algorithms. To improve the capability of resisting steganalysis algorithms, an image steganography scheme based on style transfer and quaternion exponent moments is proposed in this paper. First, the geometric invariance of quaternion exponent moments is combined to accomplish the task of embedding secret information. Next, the style transfer is performed on a stego image embedded with the secret information, and the stylized image is used to transmit through the common channel. Then, the receiver attempts to remove the style from the stylized image and to restore the stylized image back to its original appearance. For this purpose, a de-stylized network is designed to reconstruct the stego image from the stylized image. Finally, an extracting algorithm is used to extract the transmitted secret image from the reconstructed stego image. In the steganography process, the main goal is to achieve that even when the appearance and distribution of the carrier image have been changed, that should also look like an independent and normal behavior to an eavesdropper. Extensive experiments are conducted to verify the feasibility of the proposed scheme. Experimental and analysis results indicate that the proposed scheme can generate an independent and meaningful image and successfully transmit a secret image and has the ability to extract a secret image at a low bit error rate. In addition, the proposed scheme provides high security.