随着深度学习中大规模数据集需求的激增，数据所有者面临未经授权使用带来的风险，因此需要有效的版权保护措施。尽管数据集水印技术在审计和验证使用方面具有潜力，但现有方法受限于不一致的评估，阻碍了公平比较和实际应用的评估。为解决这一差距，我们提出了一种两层分类法，按实现方式（基于模型 vs. 基于模型的注入；基于模型行为 vs. 基于模型消息的验证）对方法进行分类，提供了一个结构化的跨任务分析框架。然后，我们开发了DWBench，一个统一的基准和开源工具包，用于系统评估图像数据集水印技术在分类和生成任务中的表现。使用DWBench，我们按照标准化条件、基于扰动的鲁棒性测试、多水印共存和多用户干扰评估了25种代表性方法。除了报告四种常用指标的结果外，我们还展示了两种新指标的结果：样本重要性用于细粒度水印可区分性，以及用于数据集层面审计的验证成功率，这使基准测试更加准确和可重复。关键发现揭示了固有的权衡：没有单一方法在所有场景中占主导地位；分类和生成任务需要专门的方法；现有技术在低水印率和现实多用户设置中表现出不稳定，出现较高的误报或性能下降。我们希望DWBench能促进水印可靠性和实用性的发展，从而在面对广泛的人工智能驱动的数据滥用时加强版权保护。
英文摘要：
The surging demand for large-scale datasets in deep learning has heightened the need for effective copyright protection, given the risks of unauthorized use to data owners. Although the dataset watermark technique holds promise for auditing and verifying usage, existing methods are hindered by inconsistent evaluations, which impede fair comparisons and assessments of real-world viability. To address this gap, we organize existing methods according to two key dimensions, implementation and verification, to support a consistent analysis and evaluation pipeline across tasks. Based on this framework, we develop DWBench, a unified benchmark and open-source toolkit for systematically evaluating image dataset watermark techniques in classification and generation tasks. Using DWBench, we assess 25 representative methods under standardized conditions, perturbation-based robustness tests, multi-watermark coexistence, and multi-user interference. To enable accurate and reproducible benchmarking, we use TPR@5%FPR for unified sample-level comparison and introduce the verification success rate (VSR) for dataset-level auditing. Key findings reveal that standard single-watermark evaluations tend to overestimate practical auditability. Methods that verify reliably in isolation often suffer from performance degradation at low watermarked-sample ratios, while yielding ambiguous ownership evidence in complex multi-user and multi-watermark settings. We hope that DWBench can facilitate advances in watermark reliability and practicality, thus strengthening copyright safeguards in the face of widespread AI-driven data exploitation.
Digital watermarking system is a paramount for safeguarding valuable resources and information. Digital watermarks are generally imperceptible to the human eye and ear. Digital watermark can be used in video, audio and digital images for a wide variety of applications such as copy prevention right management, authentication and filtering of internet content. The proposed system is able to protect copyright or owner identification of digital media, such as audio, image, video, or text. The system permutated the watermark and embed the permutated watermark into the wavelet coefficients of the or…
RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州高等研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Due to the recent demand of 3-D models in several applications like medical imaging, video games, among others, the necessity of implementing 3-D mesh watermarking schemes aiming to protect copyright has increased considerably. The majority of robust 3-D watermarking techniques have essentially focused on the robustness against attacks while the imperceptibility of these techniques is still a real issue. In this context, a blind robust 3-D mesh watermarking method based on mesh saliency and Quantization Index Modulation (QIM) for Copyright protection is proposed. The watermark is embedded by q…
Due to the recent demand of 3-D meshes in a wide range of applications such as video games, medical imaging, film special effect making, computer-aided design (CAD), among others, the necessity of implementing 3-D mesh watermarking schemes aiming to protect copyright has increased in the last decade. Nowadays, the majority of robust 3-D watermarking approaches have mainly focused on the robustness against attacks while the imperceptibility of these techniques is still a serious challenge. In this context, a blind robust 3-D mesh watermarking method based on mesh saliency and scalar Costa schem…
In this paper a new approach to image watermarking in wavelet domain is presented. The idea is to hide the watermark data in blocks of the block segmented image. Two schemes are presented based on this idea by embedding the watermark data in the low pass wavelet coefficients of each block. Due to low computational complexity of the proposed approach, this algorithm can be implemented in real time. Experimental results demonstrate the impercepti-bility of the proposed method and its high robustness against various attacks such as filtering, JPEG compres-sion, cropping, noise addition and geomet…
From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection
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 Chinese Academy of Sciences（中国科学院大学网络安全学院）
Toward Copyright Integrity and Verifiability via Multi-Bit Watermarking for Intelligent Transportation Systems
Beijing University of Posts and Telecommunications（北京邮电大学）；School of Cyberspace Security, Beijing University of Posts and Telecommunications（北京邮电大学网络空间安全学院）
Recently, High-Efficiency Video Coding (HEVC/H.265) has been chosen to replace previous video coding standards, such as H.263 and H.264. Despite the efficiency of HEVC, it still lacks reliable and practical functionalities to support authentication and copyright applications. In order to provide this support, several watermarking techniques have been proposed by many researchers during the last few years. However, those techniques are still suffering from many issues that need to be considered for future designs. In this paper, a Systematic Literature Review (SLR) is introduced to identify HEV…
LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
Southeast University（东南大学）；State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全全国重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术开发区（滨江）区块链与数据安全研究院）；College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）
Forging the Unforgeable: On the Feasibility of Counterfeit Watermarks in Backdoor-Based Dataset Ownership Verification
College of Cyber Security, Jinan University（济南大学网络安全学院）；School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；School of Advanced Technology, Xi’an Jiaotong-Liverpool University（西交利物浦大学前沿技术学院）
PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs
State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全全国重点实验室）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；CRRC Zhuzhou Institute & Tengen Intelligence Institute（中车株洲研究所与天恒智能研究院）
The availability of bandwidth for internet access is sufficient enough to communicate digital assets. These digital assets are subjected to various types of threats. [19] As a result of this, protection mechanism required for the protection of digital assets is of priority in research. The threat of current focus is unauthorized copying of digital assets which give boost to piracy. This under the copyright act is illegal and a robust mechanism is required to curb this kind of unauthorized copy. To safeguard the copyright digital assets, a robust digital watermarking technique is needed. The ex…
In this paper, we deal with the proof of ownership or legitimate usage of a digital content, such as an image, in order to tackle the illegitimate copy. The proposed scheme based on the combination of the watermark-ing and cancelable biometrics does not require a trusted third party, all the exchanges are between the provider and the customer. The use of cancelable biometrics permits to provide a privacy compliant proof of identity. We illustrate the robustness of this method against intentional and unintentional attacks of the watermarked content.
Digital multimedia watermarking technology had suggested in the last decade to embed copyright information in digital objects such as images, audio and video. However, the increasing use of relational database systems in many real-life applications created an ever-increasing need for watermarking database systems. As a result, watermarking relational database system is now emerging as a research area that deals with the legal issue of copyright protection of database systems. The main goal of database watermarking is to generate robust and impersistent watermark for database. In this paper we …
Digital multimedia watermarking technology was suggested in the last decade to embed copyright information in digital objects such images, audio and video. However, the increasing use of relational database systems in many real-life applications created an ever increasing need for watermarking database systems. As a result, watermarking relational database systems is now merging as a research area that deals with the legal issue of copyright protection of database systems. Approach: In this study, we proposed an efficient database watermarking algorithm based on inserting binary image watermar…
Reversible visible watermarking (RVW) is an active copyright protection mechanism. It not only transparently superimposes copyright patterns on specific positions of digital images or video frames to declare the copyright ownership information, but also completely erases the visible watermark image and thus enables restoring the original host image without any distortion. However, existing RVW algorithms mostly construct the reversible mapping mechanism for a specific visible watermarking scheme, which is not versatile. Hence, we propose a generic RVW framework to accommodate various visible w…
Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermark
School of Cyberspace Security, Guangzhou University（广州大学网络空间安全学院）；Institute of Artificial Intelligence, Guangzhou University（广州大学人工智能研究院）；School of Cyber Engineering, Xidian University（西安电子科技大学网络与信息安全学院）；School of Computer Science, Guangzhou University（广州大学计算机科学学院）
Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
University of Maryland（马里兰大学）；ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙江大学杭州国际科创中心）；Zhejiang University（浙江大学）；Northwestern University（西北大学）；Tsinghua University（清华大学）；UC Riverside（加州大学河滨分校）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Chicago（芝加哥大学）
Deep neural networks have had enormous impact on various domains of computer science, considerably outperforming previous state of the art machine learning techniques. To achieve this performance, neural networks need large quantities of data and huge computational resources, which heavily increases their construction costs. The increased cost of building a good deep neural network model gives rise to a need for protecting this investment from potential copyright infringements. Legitimate owners of a machine learning model want to be able to reliably track and detect a malicious adversary that…
In this paper, a new approach to Spread Spectrum (SS) watermarking technique is introduced. This problem is particularly interesting in the field of modern multimedia applications like internet when copyright protection of digital image is required. The approach exploits two-predecessor single attractor (TPSA) cellular automata (CA) suitability to work as efficient authentication function in wavelet based SS watermarking domain. The scheme is designed from the analytical study of state transition behaviour of non-group CA and the basic cryptography/encryption scheme is significantly different …
C. U. Shah University（C. U. Shah 大学）；Atmiya Institute of Technology & Science（Atmiya 科技学院）
The robustness and security of the biometric watermarking approach can be improved by using a multiple watermarking. This multiple watermarking proposed for improving security of biometric features and data. When the imposter tries to create the spoofed biometric feature, the invisible biometric watermark features can provide appropriate protection to multimedia data. In this paper, a biometric watermarking technique with multiple biometric watermarks are proposed in which biometric features of fingerprint, face, iris and signature is embedded in the image. Before embedding, fingerprint, iris,…
Creating a state-of-the-art deep-learning system requires vast amounts of data, expertise, and hardware, yet research into embedding copyright protection for neural networks has been limited. One of the main methods for achieving such protection involves relying on the susceptibility of neural networks to backdoor attacks, but the robustness of these tactics has been primarily evaluated against pruning, fine-tuning, and model inversion attacks. In this work, we propose a neural network "laundering" algorithm to remove black-box backdoor watermarks from neural networks even when the adversary h…
Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service
Institute of Information Engineering, Chinese Academy of Science（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Beijing Institute of Technology（北京理工大学）；University of Adelaide（阿德莱德大学）
Training deep neural networks from scratch could be computationally expensive and requires a lot of training data. Recent work has explored different watermarking techniques to protect the pre-trained deep neural networks from potential copyright infringements. However, these techniques could be vulnerable to watermark removal attacks. In this work, we propose REFIT, a unified watermark removal framework based on fine-tuning, which does not rely on the knowledge of the watermarks, and is effective against a wide range of watermarking schemes. In particular, we conduct a comprehensive study of …
SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion Models
Software Engineering Institute, East China Normal University（华东师范大学软件工程学院）；School of Computer Science and Technology, Harbin Institute of Technology (Shen Zhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）；College of Integrated Circuits, Zhejiang University（浙江大学集成电路学院）
