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 has no prior knowledge of the structure of the watermark.
We are able to effectively remove watermarks used for recent defense or copyright protection mechanisms while achieving test accuracies above 97% and 80% for both MNIST and CIFAR-10, respectively. For all backdoor watermarking methods addressed in this paper, we find that the robustness of the watermark is significantly weaker than the original claims. We also demonstrate the feasibility of our algorithm in more complex tasks as well as in more realistic scenarios where the adversary is able to carry out efficient laundering attacks using less than 1% of the original training set size, demonstrating that existing backdoor watermarks are not sufficient to reach their claims.
Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized re-distribution, watermarking approaches have been introduced in the past couple of years. We investigate the robustness and reliability of state-of-the-art deep neural network watermarking schemes. We focus on backdoor-based watermarking and propose two -- a black-box and a white-box -- attacks that remove the watermark. Our black-box attack steals the model and remove…
Toyota Technological Institute Chicago（芝加哥丰田技术研究所）
A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical data; however, the model reliably errs on watermarked examples. To gain a better foundational understanding of backdoor data poisoning attacks, we present a formal theoretical framework within which one can discuss backdoor data poisoning attacks for classification problems. We then use this to analyze important statistical and computational issues surrounding…
Backdoor-based watermarking schemes were proposed to protect the intellectual property of artificial intelligence models, especially deep neural networks, under the black-box setting. Compared with ordinary backdoors, backdoor-based watermarks need to digitally incorporate the owner's identity, which fact adds extra requirements to the trigger generation and verification programs. Moreover, these concerns produce additional security risks after the watermarking scheme has been published for as a forensics tool or the owner's evidence has been eavesdropped on. This paper proposes the capsulatio…
Delft University of Technology（代尔夫特理工大学）；Radboud University（拉德堡德大学）
Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. Building a powerful GNN model is not a trivial task, as it requires a large amount of training data, powerful computing resources, and human expertise in fine-tuning the model. Moreover, with the development of adversarial attacks, e.g., model stealing attacks, GNNs raise challenges to model authentication. To avoid copyright infringement on GNNs, verifying the ownership of the GNN models is necessary. This paper presents a watermarking framework for GNNs for both graph and node classification …
Tsinghua University（清华大学）；Shandong University（山东大学）；Wuhan University（武汉大学）；Zhongguancun Laboratory（中关村实验室）；Shandong Institute of Blockchain（山东省区块链研究院）；National Financial Cryptography Research Center（国家金融密码研究中心）
Peking University（北京大学）；Central South University（中南大学）；Fuzhou University（福州大学）；Jinan University（暨南大学）；Loughborough University（拉夫堡大学）
Federated learning (FL) allows multiple participants to collaboratively build deep learning (DL) models without directly sharing data. Consequently, the issue of copyright protection in FL becomes important since unreliable participants may gain access to the jointly trained model. Application of homomorphic encryption (HE) in secure FL framework prevents the central server from accessing plaintext models. Thus, it is no longer feasible to embed the watermark at the central server using existing watermarking schemes. In this paper, we propose a novel client-side FL watermarking scheme to tackl…
School of Control and Computer Engineering（控制与计算机工程学院）；North China Electric Power University（华北电力大学）；Research Institute（研究院）；China Unicom（中国联合网络通信集团）；Technical Department（技术部）
The rapid advancement of deep neural networks (DNNs) heavily relies on large-scale, high-quality datasets. However, unauthorized commercial use of these datasets severely violates the intellectual property rights of dataset owners. Existing backdoor-based dataset ownership verification methods suffer from inherent limitations: poison-label watermarks are easily detectable due to label inconsistencies, while clean-label watermarks face high technical complexity and failure on high-resolution images. Moreover, both approaches employ static watermark patterns that are vulnerable to detection and …
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学清华深圳国际研究生院）；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）；Shenzhen Research Institute of Big Data（深圳大数据研究院）
The rapid development of deep learning has benefited from the release of some high-quality open-sourced datasets ($e.g.$, ImageNet), which allows researchers to easily verify the effectiveness of their algorithms. Almost all existing open-sourced datasets require that they can only be adopted for academic or educational purposes rather than commercial purposes, whereas there is still no good way to protect them. In this paper, we propose a \emph{backdoor embedding based dataset watermarking} method to protect an open-sourced image-classification dataset by verifying whether it is used for trai…
Watermarking has become a plausible candidate for ownership verification and intellectual property protection of deep neural networks. Regarding image classification neural networks, current watermarking schemes uniformly resort to backdoor triggers. However, injecting a backdoor into a neural network requires knowledge of the training dataset, which is usually unavailable in the real-world commercialization. Meanwhile, established watermarking schemes oversight the potential damage of exposed evidence during ownership verification and the watermarking algorithms themselves. Those concerns dec…
PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark
State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链与数据安全研究院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Black-box Dataset Ownership Verification via Backdoor Watermarking
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Information Science and Technology, Southwest Jiaotong University（西南交通大学信息科学与技术学院）；Research Center of Artificial Intelligence, Peng Cheng Laboratory（鹏城实验室人工智能研究中心）；Ant Group（蚂蚁集团）
CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Mathematics, Sun Yat-sen University（中山大学数学学院）；Zhejiang University（浙江大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链与数据安全研究院）；Tsinghua University（清华大学）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Research Center of Artificial Intelligence, Peng Cheng Laboratory（鹏城实验室人工智能研究中心）
Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
Zhejiang University（浙江大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链与数据安全研究院）；Nanyang Technological University（南洋理工大学）
As companies continue to invest heavily in larger, more accurate and more robust deep learning models, they are exploring approaches to monetize their models while protecting their intellectual property. Model licensing is promising, but requires a robust tool for owners to claim ownership of models, i.e. a watermark. Unfortunately, current designs have not been able to address piracy attacks, where third parties falsely claim model ownership by embedding their own "pirate watermarks" into an already-watermarked model. We observe that resistance to piracy attacks is fundamentally at odds with …
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）
Cryptographic Backdoor for Neural Networks: Boon and Bane
College of Computing and Data Science, Nanyang Technological University Singapore（南洋理工大学计算与数据科学学院）；Applied Statistics Unit, Indian Statistical Institute（印度统计研究所应用统计单位）
Graph Neural Networks (GNNs) are valuable intellectual property, yet many watermarks rely on backdoor triggers that break under common model edits and create ownership ambiguity. We present InvGNN-WM, which ties ownership to a model's implicit perception of a graph invariant, enabling trigger-free, black-box verification with negligible task impact. A lightweight head predicts normalized algebraic connectivity on an owner-private carrier set; a sign-sensitive decoder outputs bits, and a calibrated threshold controls the false-positive rate. Across diverse node and graph classification datasets…
Training pipelines for machine learning (ML) based malware classification often rely on crowdsourced threat feeds, exposing a natural attack injection point. In this paper, we study the susceptibility of feature-based ML malware classifiers to backdoor poisoning attacks, specifically focusing on challenging "clean label" attacks where attackers do not control the sample labeling process. We propose the use of techniques from explainable machine learning to guide the selection of relevant features and values to create effective backdoor triggers in a model-agnostic fashion. Using multiple refer…
In order to protect the intellectual property (IP) of deep neural networks (DNNs), many existing DNN watermarking techniques either embed watermarks directly into the DNN parameters or insert backdoor watermarks by fine-tuning the DNN parameters, which, however, cannot resist against various attack methods that remove watermarks by altering DNN parameters. In this paper, we bypass such attacks by introducing a structural watermarking scheme that utilizes channel pruning to embed the watermark into the host DNN architecture instead of crafting the DNN parameters. To be specific, during watermar…
MEA-Defender: A Robust Watermark against Model Extraction Attack
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空间安全学院）；Department of Computer Science, Metropolitan College, Boston University（波士顿大学大都会学院计算机科学系）
Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
School of Cyberspace Security, Beijing University of Posts and Telecommunications（北京邮电大学网络安全学院）；Cyberspace Institute of Advanced Technology, Guangzhou University（广州大学网络空间技术研究院）；Huangpu Research School of Guangzhou University（广州大学黄埔研究学院）
University of Science and Technology of China（中国科学技术大学）；Beijing Electronic Science and Technology Institute（北京电子科技学院）
Deep convolutional neural networks have made outstanding contributions in many fields such as computer vision in the past few years and many researchers published well-trained network for downloading. But recent studies have shown serious concerns about integrity due to model-reuse attacks and backdoor attacks. In order to protect these open-source networks, many algorithms have been proposed such as watermarking. However, these existing algorithms modify the contents of the network permanently and are not suitable for integrity authentication. In this paper, we propose a reversible watermarki…
Shandong University（山东大学）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）
Deep learning techniques have made tremendous progress in a variety of challenging tasks, such as image recognition and machine translation, during the past decade. Training deep neural networks is computationally expensive and requires both human and intellectual resources. Therefore, it is necessary to protect the intellectual property of the model and externally verify the ownership of the model. However, previous studies either fail to defend against the evasion attack or have not explicitly dealt with fraudulent claims of ownership by adversaries. Furthermore, they can not establish a cle…
Fragile Model Watermark for integrity protection: leveraging boundary volatility and sensitive sample-pairing
East China Normal University（华东师范大学）；Guangxi Normal University（广西师范大学）；Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong（香港中文大学深圳大数据研究院）
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）
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）
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Boston University（波士顿大学）；University of Oregon（俄勒冈大学）
Due to the wide use of highly-valuable and large-scale deep neural networks (DNNs), it becomes crucial to protect the intellectual property of DNNs so that the ownership of disputed or stolen DNNs can be verified. Most existing solutions embed backdoors in DNN model training such that DNN ownership can be verified by triggering distinguishable model behaviors with a set of secret inputs. However, such solutions are vulnerable to model fine-tuning and pruning. They also suffer from fraudulent ownership claim as attackers can discover adversarial samples and use them as secret inputs to trigger …
