EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GCL-MIH: A Generative-Based Coverless Multi-Image Hiding Method

Liang Chen, Xianquan Zhang, Chunqiang Yu, Xinpeng Zhang, Ching-Nung Yang, Zhenjun Tang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-06 · 48 (6) · 6720-6734

DOI: 10.1109/tpami.2026.3658731 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-06. Verfasst von Liang Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Natural Science Foundation, National Natural Science Foundation of China, Guangxi Bagui Scholar Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Secure and high-capacity secret information transmission is an important task of the image hiding research. The existing image hiding methods face some critical issues: cover-based methods offer high capacity but introduce image distortion and security risks, whereas secure coverless methods have low capacity. To address these issues, this paper proposes a novel generative-based coverless multi-image hiding method called GCL-MIH, which can achieve high capacity and high security. The GCL-MIH first utilizes a feature reverse module to compress multiple secret images into multiple feature vectors and then normalizes them to generate a vector that conforms to a standard normal distribution, and finally inputs this vector into an invertible generative network (Flow-GAN) to generate a face image, enabling coverless multiple-image hiding without a predefined cover image. Experimental results demonstrate that the GCL-MIH successfully hides up to four images within a single generated face image, achieving a maximum embedding rate of 32 bpp. This capacity far exceeds those of the existing coverless methods. On the COCO test set, the generated stego images of the GCL-MIH are highly realistic (FID score: 11.98), and the recovered secret images exhibit satisfactory fidelity (the average PSNR and SSIM of four recovered secret images are 33.18 dB and 0.9412).

Förderung

  • Guangxi Natural Science Foundation
  • National Natural Science Foundation of China
  • Guangxi Bagui Scholar Project

Zitieren

APA

Chen, L., Zhang, X., Yu, C., Zhang, X., Yang, C. N., & Tang, Z. (2026). GCL-MIH: A Generative-Based Coverless Multi-Image Hiding Method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(6), 6720-6734. https://doi.org/10.1109/tpami.2026.3658731

Vancouver

Chen L, Zhang X, Yu C, Zhang X, Yang CN, Tang Z. GCL-MIH: A Generative-Based Coverless Multi-Image Hiding Method. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(6):6720-6734. doi:10.1109/tpami.2026.3658731

BibTeX
@article{Chen2026,
  author = {Chen, Liang and Zhang, Xianquan and Yu, Chunqiang and Zhang, Xinpeng and Yang, Ching-Nung and Tang, Zhenjun},
  title = {GCL-MIH: A Generative-Based Coverless Multi-Image Hiding Method},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {6},
  pages = {6720--6734},
  doi = {10.1109/tpami.2026.3658731}
}
Kostenlos starten →