# De-END: Decoder-driven Watermarking Network

arXiv: https://arxiv.org/abs/2206.13032 · HTML: https://mlsanity.com/paper/2206.13032/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2022.

## Built on by (most cited first, 12 of 12)

- [Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space](https://mlsanity.com/paper/2404.00230/) (2024)
- [Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integrity](https://mlsanity.com/paper/2509.07647/) (2025)
- [MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retraining](https://mlsanity.com/paper/2404.05607/) (2024)
- [A Brief Yet In-Depth Survey of Deep Learning-Based Image Watermarking](https://mlsanity.com/paper/2308.04603/) (2023)
- [FontGuard: A Robust Font Watermarking Approach Leveraging Deep Font Knowledge](https://mlsanity.com/paper/2504.03128/) (2025)
- [InvZW: Invariant Feature Learning via Noise-Adversarial Training for Robust Image Zero-Watermarking](https://mlsanity.com/paper/2506.20370/) (2025)
- [RoWSFormer: A Robust Watermarking Framework with Swin Transformer for Enhanced Geometric Attack Resilience](https://mlsanity.com/paper/2409.14829/) (2024)
- [Learning Generalizable and Efficient Image Watermarking via Hierarchical Two-Stage Optimization](https://mlsanity.com/paper/2508.08667/) (2025)
- [MolMark: Safeguarding Molecular Structures through Learnable Atom-Level Watermarking](https://mlsanity.com/paper/2508.17702/) (2025)
- [Enhancing Robustness in Post-Processing Watermarking: An Ensemble Attack Network Using CNNs and Transformers](https://mlsanity.com/paper/2509.03006/) (2025)
- [Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking](https://mlsanity.com/paper/2602.21849/) (2026)
- [High-Capacity Robust Watermarking Technology for High-Resolution Images](https://mlsanity.com/paper/2607.17056/) (2026)

## Abstract (arXiv)

With recent advances in machine learning, researchers are now able to solve traditional problems with new solutions. In the area of digital watermarking, deep-learning-based watermarking technique is being extensively studied. Most existing approaches adopt a similar encoder-driven scheme which we name END (Encoder-NoiseLayer-Decoder) architecture. In this paper, we revamp the architecture and creatively design a decoder-driven watermarking network dubbed De-END which greatly outperforms the existing END-based methods. The motivation for designing De-END originated from the potential drawback we discovered in END architecture: The encoder may embed redundant features that are not necessary for decoding, limiting the performance of the whole network. We conducted a detailed analysis and found that such limitations are caused by unsatisfactory coupling between the encoder and decoder in END. De-END addresses such drawbacks by adopting a Decoder-Encoder-Noiselayer-Decoder architecture. In De-END, the host image is firstly processed by the decoder to generate a latent feature map instead of being directly fed into the encoder. This latent feature map is concatenated to the original watermark message and then processed by the encoder. This change in design is crucial as it makes the feature of encoder and decoder directly shared thus the encoder and decoder are better coupled. We conducted extensive experiments and the results show that this framework outperforms the existing state-of-the-art (SOTA) END-based deep learning watermarking both in visual quality and robustness. On the premise of the same decoder structure, the visual quality (measured by PSNR) of De-END improves by 1.6dB (45.16dB to 46.84dB), and extraction accuracy after JPEG compression (QF=50) distortion outperforms more than 4% (94.9% to 99.1%).