# A Robust Blind Watermarking Using Convolutional Neural Network

arXiv: https://arxiv.org/abs/1704.03248 · HTML: https://mlsanity.com/paper/1704.03248/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2017.

## Built on by (most cited first, 11 of 11)

- [Robust Multi-bit Natural Language Watermarking through Invariant Features](https://mlsanity.com/paper/2305.01904/) (2023)
- [Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms](https://mlsanity.com/paper/2212.12678/) (2022)
- [Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography](https://mlsanity.com/paper/2107.09287/) (2021)
- [Learning to Immunize Images for Tamper Localization and Self-Recovery](https://mlsanity.com/paper/2210.15902/) (2022)
- [Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyond](https://mlsanity.com/paper/2306.00419/) (2023)
- [RWN: Robust Watermarking Network for Image Cropping Localization](https://mlsanity.com/paper/2110.05687/) (2021)
- [A Robust Document Image Watermarking Scheme using Deep Neural Network](https://mlsanity.com/paper/2202.13067/) (2022)
- [A Deep Learning-based Audio-in-Image Watermarking Scheme](https://mlsanity.com/paper/2110.02436/) (2021)
- [Hiding Images into Images with Real-world Robustness](https://mlsanity.com/paper/2110.05689/) (2021)
- [A Brief Yet In-Depth Survey of Deep Learning-Based Image Watermarking](https://mlsanity.com/paper/2308.04603/) (2023)
- [Deep Learning-based Dual Watermarking for Image Copyright Protection and Authentication](https://mlsanity.com/paper/2502.18501/) (2025)

## Abstract (arXiv)

This paper introduces a blind watermarking based on a convolutional neural network (CNN). We propose an iterative learning framework to secure robustness of watermarking. One loop of learning process consists of the following three stages: Watermark embedding, attack simulation, and weight update. We have learned a network that can detect a 1-bit message from a image sub-block. Experimental results show that this learned network is an extension of the frequency domain that is widely used in existing watermarking scheme. The proposed scheme achieved robustness against geometric and signal processing attacks with a learning time of one day.