Visible watermarks are widely-used in images to protect copyright ownership. Analyzing watermark removal helps to reinforce the anti-attack techniques in an adversarial way. Current removal methods normally leverage image-to-image translation techniques. Nevertheless, the uncertainty of the size, shape, color and transparency of the watermarks set a huge barrier for these methods. To combat this, we combine traditional watermarked image decomposition into a two-stage generator, called Watermark-Decomposition Network (WDNet), where the first stage predicts a rough decomposition from the whole watermarked image and the second stage specifically centers on the watermarked area to refine the removal results. The decomposition formulation enables WDNet to separate watermarks from the images rather than simply removing them. We further show that these separated watermarks can serve as extra nutrients for building a larger training dataset and further improving removal performance. Besides, we construct a large-scale dataset named CLWD, which mainly contains colored watermarks, to fill the vacuum of colored watermark removal dataset. Extensive experiments on the public gray-scale dataset LVW and CLWD consistently show that the proposed WDNet outperforms the state-of-the-art approaches both in accuracy and efficiency. The code and CLWD dataset are publicly available at https://github.com/MRUIL/WDNet.
Sun Yat-sen University（中山大学）；Shanghai University of Finance and Economics（上海财经大学）；Shanghai Jiao Tong University（上海交通大学）；The University of Edinburgh（爱丁堡大学）；Zhejiang University（浙江大学）
Visible watermark plays an important role in image copyright protection and the robustness of a visible watermark to an attack is shown to be essential. To evaluate and improve the effectiveness of watermark, watermark removal attracts increasing attention and becomes a hot research top. Current methods cast the watermark removal as an image-to-image translation problem where the encode-decode architectures with pixel-wise loss are adopted to transfer the transparent watermarked pixels into unmarked pixels. However, when a number of realistic images are presented, the watermarks are more likel…
Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal
School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Research Institute of Sun Yat-sen University in Shenzhen（中山大学深圳研究院）；Afirstsoft
Towards Robust Content Watermarking Against Removal and Forgery Attacks
Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）；University of Waterloo（滑铁卢大学）
本文提出Instance-Specific watermarking with Two-Sided detection方法，通过动态控制水印注入时间和模式提升鲁棒性，有效对抗移除和伪造攻击。
Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach
Donghua University（东华大学）；Shanghai Jiao Tong University（上海交通大学）；Xidian University（西安电子科技大学）；Hefei University of Technology（合肥工业大学）；East China Normal University（华东师范大学）
Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removal
Hong Kong JC STEM Lab of Smart City and Department of Computer Science, City University of Hong Kong（香港JC STEM实验室及城市大学计算机科学系）；Infocomm Technology Cluster, Singapore Institute of Technology（新加坡理工学院信息通信技术集群）；College of Information Science & Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科学与技术大学计算机科学与工程学院）；Department of Electronic and Electrical Engineering, University College London（伦敦大学学院电子与电气工程系）
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence（人工智能研究院）；Hefei Comprehensive National Science Center（合肥综合国家科学中心）；Michigan State University（密歇根州立大学）；Cisco Research（思科研究）
School of Software, Northwestern Polytechnical University（西北工业大学软件学院）；National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（空天地海一体化大数据应用技术国家工程实验室）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；Peng Cheng Laboratory（鹏城实验室）；School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）
MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能教育部重点实验室）；INTSIG
Superimposing visible watermarks on images provides a powerful weapon to cope with the copyright issue. Watermark removal techniques, which can strengthen the robustness of visible watermarks in an adversarial way, have attracted increasing research interest. Modern watermark removal methods perform watermark localization and background restoration simultaneously, which could be viewed as a multi-task learning problem. However, existing approaches suffer from incomplete detected watermark and degraded texture quality of restored background. Therefore, we design a two-stage multi-task network t…
Digital watermark is a commonly used technique to protect the copyright of medias. Simultaneously, to increase the robustness of watermark, attacking technique, such as watermark removal, also gets the attention from the community. Previous watermark removal methods require to gain the watermark location from users or train a multi-task network to recover the background indiscriminately. However, when jointly learning, the network performs better on watermark detection than recovering the texture. Inspired by this observation and to erase the visible watermarks blindly, we propose a novel two-…
University of Chinese Academy of Sciences（中国科学院大学）；Sun Yat-sen University（中山大学）；Institute of Information Engineering, CAS（中国科学院信息工程研究所）；Ant Group（蚂蚁集团）；Tencent Security Zhuque Lab（腾讯安全朱雀实验室）；University of Munich（慕尼黑大学）
As a common security tool, visible watermarking has been widely applied to protect copyrights of digital images. However, recent works have shown that visible watermarks can be removed by DNNs without damaging their host images. Such watermark-removal techniques pose a great threat to the ownership of images. Inspired by the vulnerability of DNNs on adversarial perturbations, we propose a novel defence mechanism by adversarial machine learning for good. From the perspective of the adversary, blind watermark-removal networks can be posed as our target models; then we actually optimize an imperc…
Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of the Chinese Academy of Sciences（中国科学院大学网络安全学院）；Nanyang Technological University（南洋理工大学）；ShanghaiTech University（上海科技大学）
Perceptive self-supervised learning network for noisy image watermark removal
Northwestern Polytechnical University（西北工业大学）；National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（空天地一体化大数据应用技术国家工程实验室）；School of Software（软件学院）；School of Electronics and Information（电子信息学院）；School of Computer Science（计算机学院）；Guangxi Key Lab of Multisource Information Mining & Security（广西多源信息挖掘与安全重点实验室）；College of Computer Science & Engineering（计算机科学与工程学院）
WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning
School of Software and Engineering, South China University of Technology（华南理工大学软件学院）；Peng Cheng Laboratory（鹏城实验室）；Tencent Wechat Department（腾讯微信事业群）；School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机学院）；Xidian University（西安电子科技大学）
In recent years as the internet age continues to grow, sharing images on social media has become a common occurrence. In certain cases, watermarks are used as protection for the ownership of the image, however, in more cases, one may wish to remove these watermark images to get the original image without obscuring. In this work, we proposed a deep learning method based technique for visual watermark removal. Inspired by the strong image translation performance of the U-structure, an end-to-end deep neural network model named AdvancedUnet is proposed to extract and remove the visual watermark s…
Deakin University（迪肯大学）；Huazhong University of Science and Technology（华中科技大学）；Qilu University of Technology（齐鲁工业大学）；Shandong Computer Science Center（山东省计算机科学中心）；Swinburne University of Technology（斯威本科技大学）
Fine-tuning attacks are effective in removing the embedded watermarks in deep learning models. However, when the source data is unavailable, it is challenging to just erase the watermark without jeopardizing the model performance. In this context, we introduce Attention Distraction (AD), a novel source data-free watermark removal attack, to make the model selectively forget the embedded watermarks by customizing continual learning. In particular, AD first anchors the model's attention on the main task using some unlabeled data. Then, through continual learning, a small number of \textit{lures}…
Box-Free Model Watermarks Are Prone to Black-Box Removal Attacks
School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；Infocomm Technology (ICT) Cluster, Singapore Institute of Technology (SIT)（新加坡理工学院信息通信技术集群）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机系）
Towards Robust Model Watermark via Reducing Parametric Vulnerability
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Ant Group（蚂蚁集团）；The University of Tokyo（东京大学）；Peng Cheng Laboratory（鹏城实验室）
On Function-Coupled Watermarks for Deep Neural Networks
The Chinese University of Hong Kong（香港中文大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；University of Electronic Science and Technology of China（电子科技大学）
Deep neural networks have been widely applied and achieved great success in various fields. As training deep models usually consumes massive data and computational resources, trading the trained deep models is highly demanded and lucrative nowadays. Unfortunately, the naive trading schemes typically involves potential risks related to copyright and trustworthiness issues, e.g., a sold model can be illegally resold to others without further authorization to reap huge profits. To tackle this problem, various watermarking techniques are proposed to protect the model intellectual property, amongst…
Digitized documents such as scientific articles, tax forms, invoices, contract papers, historic texts are widely used nowadays. These document images could be degraded or damaged due to various reasons including poor lighting conditions, shadow, distortions like noise and blur, aging, ink stain, bleed-through, watermark, stamp, etc. Document image enhancement plays a crucial role as a pre-processing step in many automated document analysis and recognition tasks such as character recognition. With recent advances in deep learning, many methods are proposed to enhance the quality of these docume…
