近年来，基于深度神经网络（DNN）的水印技术发展迅速，表现出卓越的性能。当前最先进的基于DNN的水印技术不仅在鲁棒性上超越了经典水印技术，还展现出对多种图像操作手段的抵抗能力。本文针对不同的基于DNN的水印技术开展了详尽的安全分析，提出了一类名为基于深度学习的覆写（Deep Learning-based OVErwriting, DLOVE）攻击的新型攻击方法，该方法利用对抗机器学习技术，可将含水印图像中的原始嵌入水印覆写为目标水印。据我们所知，这类攻击尚属首次提出。我们考虑了水印被用于设计构建对抗攻击的场景，分别在白盒和黑盒设置下开展研究。为验证该攻击的适配性与有效性，我们针对7种不同的水印技术——HiDDeN、ReDMark、PIMoG、Stegastamp、Aparecium、Distortion Agostic Deep Watermarking以及Hiding Images in an Image——实施了DLOVE攻击分析，这些技术均采用不同方法生成视觉上难以察觉的含水印图像。我们在多种约束条件下对这些水印技术开展的攻击分析，揭示了基于DNN的水印技术存在的安全漏洞，大量实验结果验证了DLOVE的攻击能力。我们提出将DLOVE作为基准安全分析工具，用于测试未来基于深度学习的水印技术的鲁棒性。
英文摘要：
Recent developments in Deep Neural Network (DNN) based watermarking techniques have shown remarkable performance. The state-of-the-art DNN-based techniques not only surpass the robustness of classical watermarking techniques but also show their robustness against many image manipulation techniques. In this paper, we performed a detailed security analysis of different DNN-based watermarking techniques. We propose a new class of attack called the Deep Learning-based OVErwriting (DLOVE) attack, which leverages adversarial machine learning and overwrites the original embedded watermark with a targeted watermark in a watermarked image. To the best of our knowledge, this attack is the first of its kind. We have considered scenarios where watermarks are used to devise and formulate an adversarial attack in white box and black box settings. To show adaptability and efficiency, we launch our DLOVE attack analysis on seven different watermarking techniques, HiDDeN, ReDMark, PIMoG, Stegastamp, Aparecium, Distortion Agostic Deep Watermarking and Hiding Images in an Image. All these techniques use different approaches to create imperceptible watermarked images. Our attack analysis on these watermarking techniques with various constraints highlights the vulnerabilities of DNN-based watermarking. Extensive experimental results validate the capabilities of DLOVE. We propose DLOVE as a benchmark security analysis tool to test the robustness of future deep learning-based watermarking techniques.
With the growing popularity of the Internet, digital images are used and transferred more frequently. Although this phenomenon facilitates easy access to information, it also creates security concerns and violates intellectual property rights by allowing illegal use, copying, and digital content theft. Using watermarks in digital images is one of the most common ways to maintain security. Watermarking is proving and declaring ownership of an image by adding a digital watermark to the original image. Watermarks can be either text or an image placed overtly or covertly in an image and are expect…
Shenzhen University（深圳大学）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua Berkeley Shenzhen Institute（清华-伯克利深圳学院）
Information security is a critical issue in modern society and image watermarking can effectively prevent unauthorized information access. Optical image watermarking techniques generally have advantages of parallel high-speed processing and multi-dimensional capabilities compared with digital approaches. This paper provides a comprehensive review on the research works related to optical image hiding and watermarking techniques conducted in the past decade. The past research works are focused on two major aspects, various optical systems for image hiding and the methods for embedding optical sy…
University of Burgundy（勃艮第大学）；Higher School of Technology（高等技术学院）；Faculty of Sciences, University of Mohammed V（穆罕默德五世大学理学院）
Due to the current progress in Internet, digital contents (video, audio and images) are widely used. Distribution of multimedia contents is now faster and it allows for easy unauthorized reproduction of information. Digital watermarking came up while trying to solve this problem. Its main idea is to embed a watermark into a host digital content without affecting its quality. Moreover, watermarking can be used in several applications such as authentication, copy control, indexation, Copyright protection, etc. In this paper, we propose a blind robust image watermarking approach as a solution to …
Bit-Level Triangular Content-Aware Permutation for Fragile Image Watermarking: Zero False Positive Rate, Single-Bit Sensitivity, and Arbitrary Dimension Support
Amirkabir University of Technology (Tehran Polytechnic)（阿米尔卡比尔理工大学（德黑兰理工大学））；Iran University of Science and Technology（伊朗科技大学）
This paper analyzes a revised fragile watermarking scheme proposed by Botta et al. which was developed as a revision of the watermarking scheme previously proposed by Rawat et al. A new attack is presented that allows an attacker to apply a valid watermark on tampered images, therefore circumventing the protection that the watermarking scheme under study was supposed to offer. Furthermore, the presented attack has very low computational and memory requirements.
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,…
Problems with securing IP Telephony systems, insufficient standardization and lack of security mechanisms emerged the need for new approaches and solutions. In this paper a new, alternative security architecture for voice-systems is presented. It is based on digital watermarking: a new, flexible and powerful technology that is increasingly gaining more and more attention. Besides known applications e.g. to solve copyright protection problems, we propose to use digital watermarking to secure not only transmitted audio but also signaling protocol that IP Telephony is based on.
The main theme of this application is to provide an algorithm color image watermark to manage the attacks such as rotation, scaling and translation. In the existing watermarking algorithms, those exploited robust features are more or less related to the pixel position, so they cannot be more robust against the attacks. In order to solve this problem this application focus on certain parameters rather than the pixel position for watermarking. Two statistical features such as the histogram shape and the mean of Gaussian filtered low-frequency component of images are taken for this proposed appli…
In this paper new security and control protocol for Voice over Internet Protocol (VoIP) service is presented. It is the alternative for the IETF's (Internet Engineering Task Force) RTCP (Real-Time Control Protocol) for real-time application's traffic. Additionally this solution offers authentication and integrity, it is capable of exchanging and verifying QoS and security parameters. It is based on digital watermarking and steganography that is why it does not consume additional bandwidth and the data transmitted is inseparably bound to the voice content.
Teleradiology enables medical images to be transferred over the computer networks for many purposes including clinical interpretation, diagnosis, archive, etc. In telemedicine, medical images can be manipulated while transferring. In addition, medical information security requirements are specified by the legislative rules, and concerned entities must adhere to them. In this research, we propose a new scheme based on 2-dimensional Discrete Wavelet Transform (2D DWT) to improve the robustness and authentication of medical images. In addition, the current research improves security and capacity …
In our previous researches, a new digital watermarking scheme based on chaotic iterations has been introduced. This scheme was both stego-secure and topologically secure. The stego-security is to face an attacker in the "watermark only attack" category, whereas the topological security concerns other categories of attacks. Its Lyapunov exponent is evaluated here, to quantify the chaos generated by this scheme. Keywords : Lyapunov exponent; Information hiding; Security; Chaotic iterations; Digital Watermarking.
Whereas the embedding distortion, the payload and the robustness of digital watermarking schemes are well understood, the notion of security is still not completely well defined. The approach proposed in the last five years is too theoretical and solely considers the embedding process, which is half of the watermarking scheme. This paper proposes a new measurement of watermarking security, called the effective key length, which captures the difficulty for the adversary to get access to the watermarking channel. This new methodology is applied to additive spread spectrum schemes where theoretic…
In this paper, we propose an efficient digital watermarking scheme to strengthen the security level already present in the database management system and to avoid illegal access to comprehensive content of database including patient's information. Doctors diagnose medical images by seeing Region of Interest (ROI). A ROI of a medical image is an area including important information and must be stored without any distortion. If a medical image is illegally obtained or if its content is changed, it may lead to wrong diagnosis. We substitute the part out of ROI of LSB bitplane of the image with th…
In Wireless sensor networks (WSNs), All communications between different nodes are sent out in a broadcast fashion. These networks are used in a variety of applications including military, environmental, and smart spaces. Sensors are susceptible to various types of attack, such as data modification, data insertion and deletion, or even physical capture and sensor replacement. Hence security becomes important issue in WSNs. However given the fact that sensors are resources constrained, hence the traditional intensive security algorithms are not well suited for WSNs. This makes traditional secur…
Japan Advanced Institute of Science and Technology（日本北陆先端科学技术大学院大学）
Speaker anonymization aims to suppress speaker individuality to protect privacy in speech while preserving the other aspects, such as speech content. One effective solution for anonymization is to modify the McAdams coefficient. In this work, we propose a method to improve the security for speaker anonymization based on the McAdams coefficient by using a speech watermarking approach. The proposed method consists of two main processes: one for embedding and one for detection. In embedding process, two different McAdams coefficients represent binary bits ``0" and ``1". The watermarked speech is …
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 …
The secure transmission of speech information is a significant issue faced by many security professionals and individuals. By applying voice-encryption technique any kind of encrypted sensitive speech data such as password can be transmitted. But this has the serious disadvantage that by means of cryptanalysis attack encrypted data can be compromised. Increasing the strength of encryption/decryption results in an associated increased in the cost. Additional techniques like stenography and digital watermarking can be used to conceal information in an undetectable way in audio data. However this…
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…
Natural language processing (NLP) technology has shown great commercial value in applications such as sentiment analysis. But NLP models are vulnerable to the threat of pirated redistribution, damaging the economic interests of model owners. Digital watermarking technology is an effective means to protect the intellectual property rights of NLP model. The existing NLP model protection mainly designs watermarking schemes by improving both security and robustness purposes, however, the security and robustness of these schemes have the following problems, respectively: (1) Watermarks are difficul…
Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios
Beijing Institute of Technology（北京理工大学）；School of Information Engineering, Minzu University of China（中央民族大学信息工程学院）；School of Computer Science, The University of Adelaide（阿德莱德大学计算机学院）
Machine learning is increasingly used in security-critical applications, such as autonomous driving, face recognition and malware detection. Most learning methods, however, have not been designed with security in mind and thus are vulnerable to different types of attacks. This problem has motivated the research field of adversarial machine learning that is concerned with attacking and defending learning methods. Concurrently, a different line of research has tackled a very similar problem: In digital watermarking information are embedded in a signal in the presence of an adversary. As a conseq…
This paper investigates a secure blind watermarking scheme. The main idea of the scheme not only protects the watermark information but also the embedding positions. To achieve a higher level of security, we propose a sub key generation mechanism based on the singular value decomposition and hash function, where sub keys depend on both the main key and the feature codes of the original image. The different sub keys ensure that the embedding positions are randomly selected for different original images. Watermark is embedded in the Discrete Cosine Transform (DCT) coefficients of the scrambled o…
Centre Inria de l’Université de Rennes（雷恩大学法国国家信息与自动化研究所中心）
Protecting the Intellectual Property rights of DNN models is of primary importance prior to their deployment. So far, the proposed methods either necessitate changes to internal model parameters or the machine learning pipeline, or they fail to meet both the security and robustness requirements. This paper proposes a lightweight, robust, and secure black-box DNN watermarking protocol that takes advantage of cryptographic one-way functions as well as the injection of in-task key image-label pairs during the training process. These pairs are later used to prove DNN model ownership during testing…
GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Computing and Information Technology, Great Bay University（大湾区大学计算与信息技术学院）；Pazhou Lab (Huangpu)（琶洲实验室（黄埔））
Watermarking is a technique for hiding of data in a medium coverage so that its presence is not detectable by a human eye and is recoverable only by the authorized recipient. Two of the most important features of watermarked image are transparency and robustness which are largely related to the security of watermarking algorithms. In this paper, an image watermarking scheme based on BCH error correction code in Discrete Cosine Transformation (DCT) domain is considered. Before embedding process, the watermark is encoded through BCH coding. Then it is embedded into the Discrete Cosine Transforma…
The challenges faced in the digital world are many, which could be resolved with some biometric recognition methods. These biometric recognition methods are encompassed within watermarking technology, steganography, cryptography, and many other schemes of security. These methods assist in securing digital images with the authentication of their owner. This paper briefly contextualizes the digital watermarking technique, which is referred to as Natural Preserving Transform (NPT) and Hartley Transform, which is endeavored in the face recognition process. The non-blind extraction and quasi-blind …
In this paper a blind, Secure, imperceptible and robust watermarking algorithm based on wavelet transform domain is proposed in which for more security, the watermark W is converted to a sequence and then a random binary sequence R of size n is adopted to encrypt the watermark, where n is the size of the watermark image. Afterwards, the encrypted watermark sequence W1 is generated by executing exclusive-OR operation on W and R. This generated watermark embeds into low frequency selected coefficients of Y channel wavelet decomposition of JPEG-YCbCr using LSB insertion technique. The experimenta…
Internet is one of the most valuable resources for information communication and retrievals. Most multimedia signals today are in digital formats. The digital data can be duplicated and edited with great ease which has led to a need for data integrity and protection of digital data. The security requirements such as integrity or data authentication can be met by implementing security measures using digital watermarking techniques. In this paper a blind speech watermarking algorithm that embeds the watermark signal data in the musical (sequence) host signal by using frequency masking is used. A…
The optical communication has an increasing need for security in public transmission scenarios. Here we present a protocol for cryptographic key distribution over a public network via photon-counting compressive imaging system with watermarking, which utilizes watermarking technique to distribute secure keys, and uses reconstructed images for simultaneous identity authentication and tampering identification. The watermark is embedded in the rearranged compressed measurements of the object, and then the signal is transmitted through a public network. At the receiving terminal, the legitimate us…
Digital Photo images are everywhere around us in journals, on walls, and over the Internet. However we have to be conscious that seeing does not always imply reality. Photo images become a rich subject of manipulations due to the advanced digital cameras as well as photo editing software. Accordingly, image forgery is becoming much easier using the existing tools in terms of time and accuracy, and thus the forensics of detecting an image forgery case is becoming difficult and needs more and more time and techniques to prove the image originality especially as crime evidences and court related …
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…
Multimedia security has been the aim point of considerable research activity because of its wide application area. The major technology to achieve copyright protection, content authentication, access control and multimedia security is watermarking which is the process of embedding data into a multimedia element such as image or audio, this embedded data can later be extracted from, or detected in the embedded element for different purposes. In this work, a blind watermarking algorithm based on SVD and circulant matrices has been presented. Every circulant matrix is associated with a matrix for…
In the field of information technology, information security technologies hold a special place. They ensure the security of the use of information technology. One of the urgent tasks is the protection of electronic documents during their transfer in information systems. This paper proposes a technology for protecting electronic documents containing digital images. The main idea is that the electronic document authorship protection can be implemented by digital watermark embedding in the images that are contained in this document. The paper considers three cases of using the proposed technology…
This paper is allocated to CDMA digital images watermarking for ownership verification and image authentication applications, which for more security, watermark W is converted to a sequence and then a random binary sequence R of size n is adopted to encrypt the watermark; where n is the size of the watermark. This adopting process uses a pseudo-random number generator to determine the pixel to be used on a given key. After converting the host image to YUV color space and then wavelet decomposition of Y channel, this adopted watermark is embedded into the selected subbands coefficients of Y cha…
In the cancerology domain, we were brought to make periodic mammography images to monitor tumor patients. Oracle Database Management system (DBMS) is a solution to manage these images with patient's data recorder. Knowing the large size of medical images of mammograms, the Oracle DBMS saves these images outside the Oracle database using external LOBs. The link between these images and Oracle is done through the BFILE. At this level, two problems are raised: the first problem is that access to these images can become impossible because the link is likely to be broken. The second problem is secu…
A genetic algorithm based robust blind digital watermarking scheme is presented. Starting from a binary image (the original watermark), a genetic algorithm is performed searching for a permutation of this image which is as uncorrelated as possible to the original watermark. The output of the GA is used as our final watermark, so that both security and robustness in the watermarking process is improved. Now, the original cover image is partitioned into non-overlapped square blocks (depending on the size of the watermark image). Then a (possibly extended) Hadamard transform is applied to these b…
From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
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）；Hainan Province Fang Binxing Academician Workstation（海南省方斌星院士工作站）
Dynamic watermarking schemes can enhance the cyber attack detection capability of networked control systems (NCSs). This paper presents a linear event-triggered solution to conventional dynamic watermarking (CDW) schemes. Firstly, the limitations of CDW schemes for event-triggered state estimation based NCSs are investigated. Secondly, a new event-triggered dynamic watermarking (ETDW) scheme is designed by treating watermarking as symmetric key encryption, based on the limit convergence theorem in probability. Its security property against the generalized replay attacks (GRAs) is also discusse…
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…
