Digital image watermarking used to be an important tool for copyright protection. However, as neural network-based watermark removal methods have been proposed in recent years, the embedded watermark is increasingly easy to be erased, which poses a great threat to copyright protection. To address this issue, we propose an adversarial visible watermark scheme, which combines the visible watermark with the adversarial perturbation. By attacking the watermark removal network, we maximize the resistance of visible watermark against removal while minimizing the visual distortion. To further improve the robustness against various transformations (e.g. cropping, JPEG compression), we employ the region of interest and random pre-processing to embed the adversarial visible watermark. The experimental results show that the proposed scheme can effectively resist the removal of watermarks on different datasets and network structures while having good transferability and robustness, which enables the watermark to continue to be an effective copyright protection method.

Jinwei Wang

Wanyun Huang

Jiawei Zhang

Xiangyang Luo

Bin Ma

Journal of Information Security and Applications

JOURNAL OF INFORMATION SECURITY AND APPLICATIONS (JISA) 专注于与信息安全和应用相关的原始研究和实践驱动的应用。 JISA 通过提供对现代问题和信息安全挑战的清晰看法，并确定有前景的科学和“最佳实践”解决方案，在充满活力的科研界和行业专业人士之间建立了共同的联系。 JISA 问题提供了国际知名信息安全专家和研究人员在原创研究工作和创新工业方法之间的平衡。

The Journal of Information Security and Applications (JISA) focuses on original research and practice-driven applications related to information security and its applications. JISA fosters a collaborative connection between the vibrant research community and industry professionals by providing clear insights into contemporary issues and challenges in information security, while identifying promising scientific and best practice solutions. The journal features a balance between original research work and innovative industrial approaches from internationally recognized experts and researchers in the field.

《Journal of Information Security and Applications》（JISA）专注于信息安全及其应用领域的原创研究和实践驱动的应用。JISA通过提供对现代信息安全问题和挑战的清晰视角，促进科研界与行业专业人士之间的交流与合作。期刊内容涵盖国际知名的信息安全专家和研究人员的原创研究成果，以及创新的工业应用方法，旨在为读者提供最佳实践和前沿科学解决方案。

Category	Quartile
计算机科学	2
计算机科学, 计算机信息系统	3

Adversarial watermark: A robust and reliable watermark against removal

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
COMPUTER SCIENCE, INFORMATION SYSTEMS	2