Paper
19 October 2022 ACGAN based coverless image steganography method
Yi An, Ning Yu, Shujuan Zhang, Haitao Liu, Jing Duan
Author Affiliations +
Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 1229446 (2022) https://doi.org/10.1117/12.2639718
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China
Abstract
Aiming at the problems of low load of traditional image steganography, obvious traces of information embedding, and difficulty in carrier selection, this paper proposes a carrier free steganography method based on Auxiliary Classifier Generative Adversarial Network (ACGAN). Based on the generative adversarial network, ACGAN converts the secret information into noise and inputs it into the generator together with the category label to generate a secret image with controllable content, which belongs to the category of vector synthesis and can effectively avoid the threat of steganalysis. At the same time, the image quality and information embedding capacity of the generated dense images are also significantly improved compared with previous methods. We conducted experiments on the MNIST data set. The experimental results show that this method can complete the functions of dense image generation and message extraction. While generating controllable dense images, the accuracy of message recovery has reached 94%. Verification The security advantages and feasibility of the scheme are discussed.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yi An, Ning Yu, Shujuan Zhang, Haitao Liu, and Jing Duan "ACGAN based coverless image steganography method", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 1229446 (19 October 2022); https://doi.org/10.1117/12.2639718
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Steganography

Image quality

Data hiding

Gallium nitride

Image transmission

Steganalysis

Image restoration

Back to Top