Aug 2026· 2026 7th International Conference on Computer Vision and Data Mining (ICCVDM)· pp. 266-270· 0 citations· 12 references
TL;DR
This paper proposes an adaptive framework built on an encoder-noise-decoder architecture, integrating channel-spatial attention and deformable convolutional networks (DCN) to enhance geometric robustness.
Abstract
Digital image copyright protection and traceability are critical due to widespread online dissemination. Conventional watermarking methods suffer from inherent trade-offs among robustness, imperceptibility, and security, and exhibit limited resilience against geometric distortions and deepfake-based adversarial manipulations. This paper proposes an adaptive framework built on an encoder-noise-decoder architecture, integrating channel-spatial attention and deformable convolutional networks (DCN) to enhance geometric robustness. Experiments demonstrate 98.7% extraction accuracy under combined attacks, 5.2 dB PSNR improvement over baselines, and effective defense against DLOVE overwriting attacks.
Watermarking is essential for image copyright protection and attribution, yet existing methods suffer from fundamental trade-offs among post-hoc applicability to pre-existing images, multi-bit capacity, training-free deployment, and adversarial resilience. To address these limitations, we propose a training-free waterm...
Model watermarking can be used to protect the intellectual property of deep learning models. However, existing model watermarking schemes often suffer from limited robustness and concealment. Moreover, copyright infringement issues are easily overlooked. In this paper, we propose an adaptive dynamic dual-authentication...
Yu-Hang Yang, Hong-Yun Cai, En-Ting Guo et al.· Journal of King Saud Univers...· 0 citations
Digital image watermarking technology realizes copyright traceability and content authentication by embedding copyright identification and authentication data in the host image, but traditional methods rely on manual design features, and it is difficult to balance robustness, invisibility and embedding capacity. In thi...
Jia-Wei Ding· Journal of Innovation and De...· 0 citations
Experimental results show that the proposed EDRRW model achieves an average PSNR of 41.49 dB on public test datasets, outperforming state-of-the-art methods, and enables secure and controllable watermark extraction relying on the correct private key.
Zi-Xuan Zhang, Chun-Qiang Yu, Xian-Quan Zhang et al.· Asia Conference onAsia Confe...· 0 citations
Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated content and ensuring traceable sources to prevent manipulation or misuse. Recent advances in invisible watermarking methods highlight the need to update existing benchmarkin...
Khaled Abud, A. Yakushev, Aleksandr Akimenkov et al.· Proceedings of the 34th ACM...· 0 citations