Protecting the Intellectual Property Rights (IPR) associated to Deep Neural Networks (DNNs) is a pressing need pushed by the high costs required to train such networks and the importance that DNNs are gaining in our society. Following its use for Multimedia (MM) IPR protection, digital watermarking has recently been considered as a mean to protect the IPR of DNNs. While DNN watermarking inherits some basic concepts and methods from MM watermarking, there are significant differences between the two application areas, calling for the adaptation of media watermarking techniques to the DNN scenario and the development of completely new methods. In this paper, we overview the most recent advances in DNN watermarking, by paying attention to cast it into the bulk of watermarking theory developed during the last two decades, while at the same time highlighting the new challenges and opportunities characterizing DNN watermarking. Rather than trying to present a comprehensive description of all the methods proposed so far, we introduce a new taxonomy of DNN watermarking and present a few exemplary methods belonging to each class. We hope that this paper will inspire new research in this exciting area and will help researchers to focus on the most innovative and challenging problems in the field.
Watermarking and fingerprinting of relational databases are quite proficient for ownership protection, tamper proofing, and proving data integrity. In past few years several such techniques have been proposed. A survey of almost all the work done, till date, in these fields has been presented in this paper. The techniques have been classified on the basis of how and where they embed the watermark. The analysis and comparison of these techniques on different merits has also been provided. In the end, this paper points out the direction of future research in these fields.
Watermarking has been widely adopted for protecting the intellectual property (IP) of Deep Neural Networks (DNN) to defend the unauthorized distribution. Unfortunately, the popular data-poisoning DNN watermarking scheme relies on target model fine-tuning to embed watermarks, which limits its practical applications in tackling real-world tasks. Specifically, the learning of watermarks via tedious model fine-tuning on a poisoned dataset (carefully-crafted sample-label pairs) is not efficient in tackling the tasks on challenging datasets and production-level DNN model protection. To address the a…
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…
Digital watermarking has been widely studied for the protection of intellectual property. Traditional watermarking schemes often design in a "wider" rule, which applies one general embedding mechanism to all images. But this will limit the scheme into a robustness-invisibility trade-off, where the improvements of robustness can only be achieved by the increase of embedding intensity thus causing the visual quality decay. However, a new scenario comes out at this stage that many businesses wish to give high level protection to specific valuable images, which requires high robustness and high vi…
Harvard University（哈佛大学）；University of Waterloo（滑铁卢大学）
Watermarking of deep neural networks (DNN) can enable their tracing once released by a data owner. In this paper, we generalize white-box watermarking algorithms for DNNs, where the data owner needs white-box access to the model to extract the watermark. White-box watermarking algorithms have the advantage that they do not impact the accuracy of the watermarked model. We propose Robust whIte-box GAn watermarking (RIGA), a novel white-box watermarking algorithm that uses adversarial training. Our extensive experiments demonstrate that the proposed watermarking algorithm not only does not impact…
Deep Neural Network (DNN) watermarking is a method for provenance verification of DNN models. Watermarking should be robust against watermark removal attacks that derive a surrogate model that evades provenance verification. Many watermarking schemes that claim robustness have been proposed, but their robustness is only validated in isolation against a relatively small set of attacks. There is no systematic, empirical evaluation of these claims against a common, comprehensive set of removal attacks. This uncertainty about a watermarking scheme's robustness causes difficulty to trust their depl…
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…
Deep Learning (DL) models have caused a paradigm shift in our ability to comprehend raw data in various important fields, ranging from intelligence warfare and healthcare to autonomous transportation and automated manufacturing. A practical concern, in the rush to adopt DL models as a service, is protecting the models against Intellectual Property (IP) infringement. The DL models are commonly built by allocating significant computational resources that process vast amounts of proprietary training data. The resulting models are therefore considered to be the IP of the model builder and need to …
Deep learning has been achieving top performance in many tasks. Since training of a deep learning model requires a great deal of cost, we need to treat neural network models as valuable intellectual properties. One concern in such a situation is that some malicious user might redistribute the model or provide a prediction service using the model without permission. One promising solution is digital watermarking, to embed a mechanism into the model so that the owner of the model can verify the ownership of the model externally. In this study, we present a novel attack method against watermark, …
With the increasing application value of machine learning, the intellectual property (IP) rights of deep neural networks (DNN) are getting more and more attention. With our analysis, most of the existing DNN watermarking methods can resist fine-tuning and pruning attack, but distillation attack. To address these problem, we propose a new DNN watermarking framework, Unified Soft-label Perturbation (USP), having a detector paired with the model to be watermarked, and Customized Soft-label Perturbation (CSP), embedding watermark via adding perturbation into the model output probability distributi…
Southern University of Science and Technology（南方科技大学）；Hunan University（湖南大学）；Changsha University of Science and Technology（长沙理工大学）
Image watermarking is a technique for hiding information into images that can withstand distortions while requiring the encoded image to be perceptually identical to the original image. Recent work based on deep neural networks (DNN) has achieved impressive progression in digital watermarking. Higher robustness under various distortions is the eternal pursuit of digital image watermarking approaches. In this paper, we propose DBMARK, a novel end-to-end digital image watermarking framework to deep boost the robustness of DNN-based image watermarking. The key novelty is the synergy of invertible…
This paper proposes a novel scheme for the watermarking of Deep Reinforcement Learning (DRL) policies. This scheme provides a mechanism for the integration of a unique identifier within the policy in the form of its response to a designated sequence of state transitions, while incurring minimal impact on the nominal performance of the policy. The applications of this watermarking scheme include detection of unauthorized replications of proprietary policies, as well as enabling the graceful interruption or termination of DRL activities by authorized entities. We demonstrate the feasibility of o…
Southwest Jiaotong University（西南交通大学）；University of Siena（锡耶纳大学）
DNN watermarking is receiving an increasing attention as a suitable mean to protect the Intellectual Property Rights associated to DNN models. Several methods proposed so far are inspired to the popular Spread Spectrum (SS) paradigm according to which the watermark bits are embedded into the projection of the weights of the DNN model onto a pseudorandom sequence. In this paper, we propose a new DNN watermarking algorithm that leverages on the watermarking with side information paradigm to decrease the obtrusiveness of the watermark and increase its payload. In particular, the new scheme exploi…
Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；School of Cyber Science and Engineering, Shanghai Jiao Tong University（上海交通大学网络空间安全学院）；Tsinghua University（清华大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Trigger set-based watermarking schemes have gained emerging attention as they provide a means to prove ownership for deep neural network model owners. In this paper, we argue that state-of-the-art trigger set-based watermarking algorithms do not achieve their designed goal of proving ownership. We posit that this impaired capability stems from two common experimental flaws that the existing research practice has committed when evaluating the robustness of watermarking algorithms: (1) incomplete adversarial evaluation and (2) overlooked adaptive attacks. We conduct a comprehensive adversarial e…
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…
University of Science and Technology of China（中国科学技术大学）；Microsoft Cloud AI（微软云人工智能部门）；City University of Hong Kong（香港城市大学）；Wormpex AI Research（Wormpex人工智能研究院）
The intellectual property (IP) of Deep neural networks (DNNs) can be easily ``stolen'' by surrogate model attack. There has been significant progress in solutions to protect the IP of DNN models in classification tasks. However, little attention has been devoted to the protection of DNNs in image processing tasks. By utilizing consistent invisible spatial watermarks, one recent work first considered model watermarking for deep image processing networks and demonstrated its efficacy in many downstream tasks. Nevertheless, it highly depends on the hypothesis that the embedded watermarks in the n…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）；City University of Hong Kong（香港城市大学）；Beijing Electronic Science and Technology Institute（北京电子科技学院）；Wormpex AI Research LLC（Wormpex AI研究有限责任公司）
Despite the tremendous success, deep neural networks are exposed to serious IP infringement risks. Given a target deep model, if the attacker knows its full information, it can be easily stolen by fine-tuning. Even if only its output is accessible, a surrogate model can be trained through student-teacher learning by generating many input-output training pairs. Therefore, deep model IP protection is important and necessary. However, it is still seriously under-researched. In this work, we propose a new model watermarking framework for protecting deep networks trained for low-level computer visi…
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…
Isfahan University of Technology（伊斯法罕理工大学）；University of Michigan（密歇根大学）；University of Queensland（昆士兰大学）
Due to the rapid growth of machine learning tools and specifically deep networks in various computer vision and image processing areas, application of Convolutional Neural Networks for watermarking have recently emerged. In this paper, we propose a deep end-to-end diffusion watermarking framework (ReDMark) which can be adapted for any desired transform space. The framework is composed of two Fully Convolutional Neural Networks with the residual structure for embedding and extraction. The whole deep network is trained end-to-end to conduct a blind secure watermarking. The framework is customiza…
Watermarking is an operation of embedding an information into an image in a way that allows to identify ownership of the image despite applying some distortions on it. In this paper, we presented a novel end-to-end solution for embedding and recovering the watermark in the digital image using convolutional neural networks. The method is based on spreading the message over the spatial domain of the image, hence reducing the "local bits per pixel" capacity. To obtain the model we used adversarial training and applied noiser layers between the encoder and the decoder. Moreover, we broadened the s…
With the wide application of deep neural networks, it is important to verify a host's possession over a deep neural network model and protect the model. To meet this goal, various mechanisms have been designed. By embedding extra information into a network and revealing it afterward, the watermark becomes a competitive candidate in proving integrity for deep learning systems. However, concurrent watermarking schemes can hardly be adopted for emerging distributed learning paradigms that raise extra requirements during the ownership verification. A spearheading distributed learning paradigm is f…
Canadian Institute for Cybersecurity（加拿大网络安全研究所）；University of New Brunswick（新不伦瑞克大学）
Deep learning techniques are one of the most significant elements of any Artificial Intelligence (AI) services. Recently, these Machine Learning (ML) methods, such as Deep Neural Networks (DNNs), presented exceptional achievement in implementing human-level capabilities for various predicaments, such as Natural Processing Language (NLP), voice recognition, and image processing, etc. Training these models are expensive in terms of computational power and the existence of enough labelled data. Thus, ML-based models such as DNNs establish genuine business value and intellectual property (IP) for …
With the broad application of deep neural networks, the necessity of protecting them as intellectual properties has become evident. Numerous watermarking schemes have been proposed to identify the owner of a deep neural network and verify the ownership. However, most of them focused on the watermark embedding rather than the protocol for provable verification. To bridge the gap between those proposals and real-world demands, we study the deep learning model intellectual property protection in three scenarios: the ownership proof, the federated learning, and the intellectual property transfer. …
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…
The commercialization of deep learning creates a compelling need for intellectual property (IP) protection. Deep neural network (DNN) watermarking has been proposed as a promising tool to help model owners prove ownership and fight piracy. A popular approach of watermarking is to train a DNN to recognize images with certain \textit{trigger} patterns. In this paper, we propose a novel evolutionary algorithm-based method to generate and optimize trigger patterns. Our method brings a siginificant reduction in false positive rates, leading to compelling proof of ownership. At the same time, it mai…
The functionality of a deep learning (DL) model can be stolen via model extraction where an attacker obtains a surrogate model by utilizing the responses from a prediction API of the original model. In this work, we propose a novel watermarking technique called DynaMarks to protect the intellectual property (IP) of DL models against such model extraction attacks in a black-box setting. Unlike existing approaches, DynaMarks does not alter the training process of the original model but rather embeds watermark into a surrogate model by dynamically changing the output responses from the original m…
