A Robust Blind Watermarking Using Convolutional Neural Network

Abstract

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.

arXiv comment4 pages. We are modifying this paper to submit to SPL

References in corpus (1)

• scikit-image: Image processing in Python

Cited by in corpus (19)

• A Robust Image Watermarking System Based on Deep Neural Networks
• Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms
• ROMark: A Robust Watermarking System Using Adversarial Training
• Deep Convolutional Neural Network for Identifying Seam-Carving Forgery
• Deep Learning-based Dual Watermarking for Image Copyright Protection and Authentication
• Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography
• Robust Data Hiding Using Inverse Gradient Attention
• Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach
• ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks
• An Automated and Robust Image Watermarking Scheme Based on Deep Neural Networks
• HiDDeN: Hiding Data With Deep Networks
• Distortion Agnostic Deep Watermarking
• Digital Passport: A Novel Technological Strategy for Intellectual Property Protection of Convolutional Neural Networks
• A General Approach for Using Deep Neural Network for Digital Watermarking
• From Attack to Protection: Leveraging Watermarking Attack Network for Advanced Add-on Watermarking
• Towards transformation-resilient provenance detection of digital media
• Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack
• Hiding Images into Images with Real-world Robustness
• A Deep Learning-based Audio-in-Image Watermarking Scheme