App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 8

Robust watermarking scheme with high visual quality for diffusion model generated images

He Tao
Zhou Fei
Zhou Yi
School of Communication & Information Engineering, Chongqing University of Posts & Telecommunications, Chongqing 400065, China
DOI: 10.19734/j.issn.1001-3695.2026.01.0002

Abstract

To address the challenges of source verification for diffusion-generated images and the limitations of existing watermarking methods—such as disrupted frequency integrity and insufficient coupling with generation mechanisms—this paper develops a high-quality and robust watermarking scheme named Diff-HSIM (Diffusion-based Hermitian Symmetric Intermediate-stage Modification) . The core innovation lies in the direct intervention of latent variables during the intermediate stage of the reverse diffusion sampling process, which deeply couples the watermark information with the generation trajectory and significantly enhances robustness against regeneration attacks. Simultaneously, the method constructs a structured watermark representation satisfying Hermitian symmetry within the latent frequency domain. This mathematical constraint eliminates generation distortions caused by the loss of imaginary parts during inverse transforms, effectively preserving the spectral integrity of the images. Furthermore, a dynamic classifier-free guidance strategy adaptively balances semantic consistency and watermark invisibility. Experimental results conducted on 1, 000 images generated by Stable Diffusion demonstrate that Diff-HSIM achieves a CLIP score of 0.363 while significantly outperforming baseline methods in PSNR and SSIM. Under various distortion attacks, including JPEG compression, Gaussian blurring, and iterative diffusion regeneration, the method attains an average detection performance (TPR@1%FPR) of 0.99, validating its superior robustness and practical effectiveness in complex application scenarios.

Foundation Support

国家自然科学基金资助项目(62271096)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.01.0002
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 8

Publish History

[2026-04-22] Accepted Paper

Cite This Article

何涛, 周非, 周奕. 针对扩散模型生成图像的高视觉质量鲁棒水印方案 [J]. 计算机应用研究, 2026, 43 (8). (2026-04-30). https://doi.org/10.19734/j.issn.1001-3695.2026.01.0002. (He Tao, Zhou Fei, Zhou Yi. Robust watermarking scheme with high visual quality for diffusion model generated images [J]. Application Research of Computers, 2026, 43 (8). (2026-04-30). https://doi.org/10.19734/j.issn.1001-3695.2026.01.0002. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)