# Robust Image Watermarking based on Cross-Attention and Invariant Domain Learning

arXiv: https://arxiv.org/abs/2310.05395 · HTML: https://mlsanity.com/paper/2310.05395/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 9 Oct 2023.

## Builds on (most cited first, 15 of 15)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [Robust Invisible Video Watermarking with Attention](https://mlsanity.com/paper/1909.01285/) (2019)
- [Watermarking Images in Self-Supervised Latent Spaces](https://mlsanity.com/paper/2112.09581/) (2021)
- [Distortion Agnostic Deep Watermarking](https://mlsanity.com/paper/2001.04580/) (2020)
- [DVMark: A Deep Multiscale Framework for Video Watermarking](https://mlsanity.com/paper/2104.12734/) (2021)
- [An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks](https://mlsanity.com/paper/2007.02460/) (2020)
- [LECA: A Learned Approach for Efficient Cover-agnostic Watermarking](https://mlsanity.com/paper/2206.10813/) (2022)
- [A Compact Neural Network-based Algorithm for Robust Image Watermarking](https://mlsanity.com/paper/2112.13491/) (2021)
- [A Deep Learning-based Audio-in-Image Watermarking Scheme](https://mlsanity.com/paper/2110.02436/) (2021)
- [A Brief Yet In-Depth Survey of Deep Learning-Based Image Watermarking](https://mlsanity.com/paper/2308.04603/) (2023)

## Abstract (arXiv)

Image watermarking involves embedding and extracting watermarks within a cover image, with deep learning approaches emerging to bolster generalization and robustness. Predominantly, current methods employ convolution and concatenation for watermark embedding, while also integrating conceivable augmentation in the training process. This paper explores a robust image watermarking methodology by harnessing cross-attention and invariant domain learning, marking two novel, significant advancements. First, we design a watermark embedding technique utilizing a multi-head cross attention mechanism, enabling information exchange between the cover image and watermark to identify semantically suitable embedding locations. Second, we advocate for learning an invariant domain representation that encapsulates both semantic and noise-invariant information concerning the watermark, shedding light on promising avenues for enhancing image watermarking techniques.