Article: A robust generative coverless co-steganography method of text and image Journal: International Journal of Autonomous and Adaptive Communications Systems (IJAACS) 2025 Vol.18 No.6 pp.485 - 508 Abstract: Most existing coverless image steganography methods based on image generation suffer from insufficient hiding capacity. To address this, a generative coverless co-steganography method of text and images is proposed. Secret text is first converted into noise vectors using convolutional error-correcting codes, then a container image is generated using a self-attention generative adversarial network (SAGAN). The secret image is converted into a binary sequence through pixel encoding, and a style image containing the secret information is generated by an encoder. These images are then input into the generator to produce two sets of generative stego images for transmission. The secret text is recovered using a gradient descent method based on the simulated annealing algorithm, while the secret image is recovered through the decoder. The proposed method is evaluated on CelebA and Fashion MNIST datasets. Compared to existing methods, the proposed method significantly improves capacity and efficiency, increasing hiding capacity by 1.6 times. Inderscience Publishers - linking academia, business and industry through research

Title: A robust generative coverless co-steganography method of text and image

Authors: Yuxi Deng; Yun Tan; Le Mao; Xuyu Xiang

Addresses: College of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha, 410004, China ' College of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha, 410004, China ' College of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha, 410004, China ' College of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha, 410004, China

Abstract: Most existing coverless image steganography methods based on image generation suffer from insufficient hiding capacity. To address this, a generative coverless co-steganography method of text and images is proposed. Secret text is first converted into noise vectors using convolutional error-correcting codes, then a container image is generated using a self-attention generative adversarial network (SAGAN). The secret image is converted into a binary sequence through pixel encoding, and a style image containing the secret information is generated by an encoder. These images are then input into the generator to produce two sets of generative stego images for transmission. The secret text is recovered using a gradient descent method based on the simulated annealing algorithm, while the secret image is recovered through the decoder. The proposed method is evaluated on CelebA and Fashion MNIST datasets. Compared to existing methods, the proposed method significantly improves capacity and efficiency, increasing hiding capacity by 1.6 times.

Keywords: coverless steganography; co-steganography of text and image; generative adversarial network; style transfer.

DOI: 10.1504/IJAACS.2025.150801

International Journal of Autonomous and Adaptive Communications Systems, 2025 Vol.18 No.6, pp.485 - 508

Received: 29 Jun 2024
Accepted: 10 Mar 2025
Published online: 23 Dec 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A robust generative coverless co-steganography method of text and image

Keep up-to-date