Robust Watermarking Research Articles

Medical Image Hybrid Watermark Algorithm Based on Frequency Domain Processing and Inception v3

With the widespread use of digital medical images in recent years, the efficient and secure protection of sensitive data has become an urgent issue. Existing research has mostly focused on optimizing individual techniques, lacking comprehensive solutions that integrate the strengths of different methods. This article proposes a hybrid digital watermarking algorithm for medical images based on frequency domain transformation and deep learning convolutional neural networks. The algorithm combines the advantages of traditional frequency domain watermarking methods and deep learning techniques. Specifically, the algorithm first extracts feature vectors from medical images using discrete wavelet transform and discrete cosine transform, enhancing the robustness of the image watermark. It then integrates an improved Inception v3 network, optimizing the convolutional kernel design, thereby effectively enhancing the robustness of the watermarking process. To further improve the security of the watermark, the Logistic Map is used to scramble and encrypt the watermark information, and a hash function and XOR operation are employed for zero embedding of the watermark. The watermark extraction and decryption process relies on a key provided by a third party, enabling blind extraction of the watermark without requiring the original image. Through extensive experimental data analysis and comparisons with multiple existing algorithms, the results demonstrate that the proposed hybrid watermarking algorithm excels in terms of attack resistance and robustness, significantly improving the security and reliability of medical image watermarking.

A Hybrid Domain-Based Digital Watermarking Technique for Robust and Imperceptible Image Copyright Protection

This work provides a strong digital watermarking method to attain undetectable and robust watermark embedding by combining many domain transformations and decomposition methods. To guarantee good watermark embedding and retrieval, the technique uses Discrete Wavelet Transform (DWT), Discrete Fourier Transform (DFT), Onion Peel Decomposition (OPD), Discrete Cosine Transform (DCT), and Singular Value Decomision (SVD). Using a strength value, the single values of the carrier picture are changed to incorporate the watermark, therefore guaranteeing low distortion and great imperceptibility. The sequence of transforms is reversed during extraction to faithfully retrieve the watermark. Under several assault scenarios—including JPEG compression, Gaussian noise, salt-and-pepper noise, scaling, cropping, and blurring—a thorough investigation was done to assess resilience. Performance was evaluated using the normalised cross-correlation (NCC) metric—which measures the resemblance between the original and extracted watermark. With an average NCC of 0.99 over all attacks, the proposed system matched or surpassed present state-of- the-art methods. The technique also generated a strong Mean Structural Similarity Index Metric (MSSIM) of 0.9966, the lowest Mean Absolute Error (MAE) of 4.2729, and the highest Peak Signal-to-- Noise Ratio (PSNR) of 36.0477.Comparatively with both random and non-random distribution approaches, comparison with average NCC values of 0.98 and 0.99 correspondingly indicated significant resilience. The random spread method exhibited higher resistance to blurring attacks, even if the non-random spread strategy was best in scaling and cropping attacks. Visual examinations confirmed considerable similarity between the watermarked and retrieved images under all attack scenarios. These results show how effectively the proposed approach balances imperceptibility and robustness, hence ensuring dependability for safe digital watermarking applications in demanding surroundings.

ModelShield: Adaptive and Robust Watermark against Model Extraction Attack

ModelShield: Adaptive and Robust Watermark against Model Extraction Attack

A DWT-DCT-SVD Based Robust Watermark Method for Image Copyright Protection

A DWT-DCT-SVD Based Robust Watermark Method for Image Copyright Protection

DFCL: Dual-pathway fusion contrastive learning for blind single-image visible watermark removal.

Digital image watermarking is a prevalent method for image copyright protection. As watermark embedding techniques evolve, research in copyright protection has increasingly extended into watermark removal. Recent advancements in deep learning and generative technologies have led to the development of public watermark removal solutions, addressing issues such as plagiarized, illegal, or outdated watermarks while driving significant improvements in robust watermark embedding. Traditional image restoration often requires the manual selection of watermark mask regions, while common blind visible watermark removal techniques struggle with watermark detection accuracy and post-removal visual quality. To address these challenges, this paper introduces a dual-pathway fusion contrastive learning approach for blind single-image visible watermark removal. We conduct dual-pathway training of the image and gradient map, enhancing high-frequency feature acquisition and the accuracy of watermark spatial positioning through feature fusion. Additionally, contrastive learning ensures that the results closely resemble the original watermark-free images while distancing themselves from watermark content, resulting in improved background visual quality. Importantly, our blind watermark removal algorithm does not require additional watermark images or mask regions. Extensive experiments on three challenging benchmark datasets demonstrate the effectiveness of our approach in overcoming the limitations of existing methods.

Robust Watermarking Algorithm for Screen-Shooting Images Based on Pattern Complexity JND Model

Robust Watermarking Algorithm for Screen-Shooting Images Based on Pattern Complexity JND Model

Latent Diffusion Models for Image Watermarking: A Review of Recent Trends and Future Directions

Recent advancements in deep learning-based generative models have simplified image generation, increasing the need for improved source tracing and copyright protection, especially with the efficient, high-quality output of latent diffusion models (LDMs) raising concerns about unauthorized use. This paper provides a comprehensive review of watermarking techniques applied to latent diffusion models, focusing on recent trends and the potential utility of these approaches. Watermarking using latent diffusion models offers the potential to overcome these limitations by embedding watermarks in the latent space during the image generation process. This represents a new paradigm of watermarking that leverages a degree of freedom unavailable in traditional watermarking techniques and underscores the need to explore the potential advancements in watermark technology. LDM-based watermarking allows for the natural internalization of watermarks within the content generation process, enabling robust watermarking without compromising image quality. We categorize the methods based on embedding strategies and analyze their effectiveness in achieving key functionalities—source tracing, copyright protection, and AI-generated content identification. The review highlights the strengths and limitations of current techniques and discusses future directions for enhancing the robustness and applicability of watermarking in the evolving landscape of generative AI.

A Novel Face Swapping Detection Scheme Using the Pseudo Zernike Transform Based Robust Watermarking

The rapid advancement of Artificial Intelligence Generated Content (AIGC) has significantly accelerated the evolution of Deepfake technology, thereby introducing escalating social risks due to its potential misuse. In response to these adverse effects, researchers have developed defensive measures, including passive detection and proactive forensics. Although passive detection has achieved some success in identifying Deepfakes, it encounters challenges such as poor generalization and decreased accuracy, particularly when confronted with anti-forensic techniques and adversarial noise. As a result, proactive forensics, which offers a more resilient defense mechanism, has garnered considerable scholarly interest. However, existing proactive forensic methodologies often fall short in terms of visual quality, detection accuracy, and robustness. To address these deficiencies, we propose a novel proactive forensic approach that utilizes pseudo-Zernike moment robust watermarking. This method is specifically designed to enhance the detection and analysis of face swapping by transforming facial data into a binary bit stream and embedding this information within the non-facial regions of video frames. Our approach facilitates the detection of Deepfakes while preserving the visual integrity of the video content. Comprehensive experimental evaluations have demonstrated the robustness of this method against standard signal processing operations and its superior performance in detecting Deepfake manipulations.

A set of embedding rules in IWT for watermark embedding in image watermarking

The development of new technologies has made image watermarking crucial in the digital era to preserve and protect illegal distribution of images against unauthorized users. This paper presents a robust image watermarking technique that employs a set of embedding rules in the three-level of integer wavelet transform (IWT). The proposed method aims to achieve high robustness of image watermarking while maintaining the imperceptibility. The proposed scheme divides the red and green layers into non-overlapping 16×16 blocks. Three levels of IWT are applied to obtain 2×2 LL sub-band, four coefficients of IWT are then modified based on the proposed set of rules for embedding watermark. The experimental results demonstrate a comparison of the proposed embedding and the existing methods. The proposed scheme produced an average NC value of 0.965 against the median filter. The results also showed the imperceptibility of the the image with a PSNR of 45.1760 db and SSIM of 0.9995.

REVIEW OF METHODS FOR EMBEDDING DIGITAL WATERMARKS FOR AUDIO FILE PROTECTION

The article presents an analysis of modern approaches to audio information protection using digital watermarks. It discusses various watermark embedding methods, including those based on the time, frequency, and timefrequency domains. Special attention is given to the characteristics of watermark robustness and imperceptibility, which are critical for ensuring high sound quality and reliable protection against attacks. Methods based on transformations, such as the discrete cosine transform (DCT), as well as adaptive approaches that take into account the properties of audio files, are analyzed. The article also provides an overview of criteria for evaluating the effectiveness of watermarking methods, such as signal-to-noise ratio (SNR) and detection probability. The conclusions of the study emphasize the need for careful selection of methods to achieve an optimal balance between protection, sound quality, and resistance to manipulation.

PoWBWM: Proof of work consensus cryptographic blockchain-based adaptive watermarking system for tamper detection applications

Image tamper detection is a challenging area in multimedia research. The advances in photography technology have made it possible to capture real-time high-dynamic-range (HDR) images through an iPhone or an Android device, which highlights the need for rigorous research on HDR images for tamper detection, and localization. The algorithms built for standard images may affect the watermark visibility when it is applied to HDR images as this produces high perceptual variations in the image compared to the original. To tackle this problem, we presented a Proof of Work consensus blockchain watermarking scheme combined with a convolution attention model (PoWBWM) system for tamper detection and localization. The system utilizes a Convolution Attention model (CoAtNet) to generate robust watermarks. A quaternion graph-based transform (QGBT) for embedding, ensuring imperceptibility and robustness. A fuzzy inference system optimizes embedding regions and factors based on human visual system characteristics. The system's security is enhanced through blockchain's proof-of-work (consensus) mechanism, providing a semi-blind watermarking scheme that authenticates ownership and detects tampering efficiently. The security is ensured only when the embedded hash key is authentic with its previous block to proceed further extraction process. The proposed algorithm's performance is evaluated in terms of its visibility by Peak-Signal-to-Noise-Ratio (PSNR), Structural Similarity Index (SSIM), and the perceptual quality of an HDR image is additionally measured by the Visual Dynamic Predictor (VDP) metric. On the other hand, the robustness performance is measured by Normalized Correlation Coefficient (NCC) and Bit Error Rate (BER). The experimental results for CASIA images achieved the highest PSNR value of 63.84 dB, and the SSIM value of 1.000, whereas the maximum VDP value obtained for HDR images is 98.02. In comparison with the existing system, the experimental findings of the suggested model show an effective tamper detection watermarking system as well as a robust against both intentional and unintentional attacks with an average NCC value of 0.98.

Invisible and robust watermarking model based on hierarchical residual fusion multi-scale convolution

In current deep learning based watermarking technologies, it remains challenging to fully integrate the features of watermark and cover image. Most watermarking models with fixed-size kernel convolution exhibit restricted feature extraction ability, leading to incomplete feature fusion. To address this issue, a hierarchical residual fusion multi-scale convolution (HRFMS) module is designed. The method extracts image features from various receptive fields and implements feature interaction by residual connection. To produce watermarked image with high visual quality and attack resistance, a watermarking model based on the HRFMS is devised to achieve multi-scale feature fusion. Moreover, to minimize image distortion caused by watermark information, an attention mask layer is designed to guide the distribution of watermark information. The experimental results demonstrate that the invisibility and the robustness of the HRFMSNet are excellent. The watermarked images generated by the HRFMSNet are nearly visually indistinguishable from the cover images. The average peak signal-to-noise ratio of the watermarked images is 37.13 dB, and most of the bit error rates of the decoded messages are below 0.02.

Attack-Defending Contrastive Learning for Volumetric Medical Image Zero-Watermarking

Zero-watermarking is an emerging distortion-free copyright protection method for volumetric medical images. However, achieving both robustness against various malicious attacks and distinguishability between individual images remains challenging. In this paper, we propose a novel attack-defending contrastive learning zero-watermarking scheme (ADCL-ZW) to tackle the above challenge using deep learning-based representations. In our approach, we design an attack-defending data enrichment mechanism to enhance the watermarking robustness by generating a large number of image samples under various watermarking attacks. Subsequently, features for both watermarking distinguishability and robustness are enhanced through application of a contrastive loss. In particular, we implement a dual-stream Siamese network architecture to effectively handle both signal attacks and geometric attacks in order to enhance the wartermarking performance. Experimental results demonstrate that ADCL-ZW achieves stronger watermarking robustness and a better tradeoff between watermarking robustness and distinguishability compared with state-of-the art zero-watermarking methods. One of the highlighted metrics the false negative rate of ADCL-ZW achieves 0.01 when a fixed false positive rate is set to 1%, which is more than 13.3 times better than the benchmark methods.

A Compressed Domain Robust Video Watermarking Resists Geometric Attack

The widespread utilization of mobile devices and the proliferation of video content, facilitated by communication networks, has unfortunately led to issues such as data piracy, illegal usage, and unauthorized sharing. To address these challenges, digital watermarking emerges as a crucial tool, serving purposes such as authentication, maintaining integrity, and identifying rightful owners. In the realm of video watermarking, two primary categories exist: watermarking in the compressed domain and watermarking in the uncompressed domain. Compressed domain watermarking involves expedited data processing through partial video decoding, whereas uncompressed domain watermarking requires more time. This article proposes a novel video watermarking methodology designed specifically to withstand geometric attacks. The proposed method aims to dynamically embed watermarks within video content, thereby enhancing resilience against various geometric distortions. Geometric attacks, including scaling, rotation, cropping, and translation, pose significant challenges in digital watermarking and are thus a focal point of this research. The objective is to integrate this approach with complex video coding standards, leveraging compression domain techniques to fortify resistance against geometric attacks. Tests show that the suggested video watermarking system works well. Not only does it excel in safeguarding against geometric attacks, but it also mitigates perceptual quality degradation, thus ensuring a balance between robustness and visual fidelity. As the prevalence of video content continues to grow, robust watermarking techniques like the one presented here play a vital role in preserving intellectual property rights and ensuring the integrity of multimedia content in the digital age.

Enhanced Security and Robustness in Color Image Watermarking Using DWT-HD and Quaternion SVD under Hybrid Attacks

Enhanced Security and Robustness in Color Image Watermarking Using DWT-HD and Quaternion SVD under Hybrid Attacks

Digital watermarking algorithm for QR code based on hybrid PSOGWO optimization

Abstract With the rapid development of digital media, QR codes have become widely used as an important medium for information transmission. However, this also presents serious security challenges, such as frequent image infringement and inevitable compression and scaling issues during data transfer. These challenges directly threaten the effectiveness and integrity of image information, and effective protection measures must be taken. Under this background, digital watermarking technology comes into being as an innovative method to enhance security. This paper presents an innovative Hybrid Particle Swarm Optimization and Gray Wolf optimization (HPG) algorithm, which combines the advantages of PSO and overcomes the limitations of traditional GWO algorithm. The algorithm is further improved by using Bernoulli chaotic mapping and nonlinear convergence factor. The experiments focus on the global and local search balance of the algorithm and its ability to resist repeated scaling attacks. The results show that the nonlinear convergence factor of HPG algorithm slows down the iteration speed at the initial stage, strengthens the global search, and avoids falling into the local optimal. In the later stage, the iteration is accelerated to improve the local search speed and convergence efficiency, thus optimizing the performance of the algorithm and ensuring the safety and quality of image information. In addition, the algorithm has better performance in balancing imperceptibility and robustness of digital watermarking, and its peak signal-to-noise ratio (PSNR) is higher. Even with many scaling iterations, the normalized correlation (NC) value is still close to 1. Compared with the existing typical algorithms, HPG algorithm is more robust to repeated scaling attacks.

A Decentralized Digital Watermarking Framework for Secure and Auditable Video Data in Smart Vehicular Networks

Thanks to the rapid advancements in Connected and Automated Vehicles (CAVs) and vehicular communication technologies, the concept of the Internet of Vehicles (IoVs) combined with Artificial Intelligence (AI) and big data promotes the vision of an Intelligent Transportation System (ITS). An ITS is critical in enhancing road safety, traffic efficiency, and the overall driving experience by enabling a comprehensive data exchange platform. However, the open and dynamic nature of IoV networks brings significant performance and security challenges to IoV data acquisition, storage, and usage. To comprehensively tackle these challenges, this paper proposes a Decentralized Digital Watermarking framework for smart Vehicular networks (D2WaVe). D2WaVe consists of two core components: FIAE-GAN, a novel feature-integrated and attention-enhanced robust image watermarking model based on a Generative Adversarial Network (GAN), and BloVA, a Blockchain-based Video frames Authentication scheme. By leveraging an encoder–noise–decoder framework, trained FIAE-GAN watermarking models can achieve the invisibility and robustness of watermarks that can be embedded in video frames to verify the authenticity of video data. BloVA ensures the integrity and auditability of IoV data in the storing and sharing stages. Experimental results based on a proof-of-concept prototype implementation validate the feasibility and effectiveness of our D2WaVe scheme for securing and auditing video data exchange in smart vehicular networks.

An adaptive robust watermarking scheme based on chaotic mapping

Digital images have become an important way of transmitting information, and the risk of attacks during transmission is increasing. Image watermarking is an important technical means of protecting image information security and plays an important role in the field of information security. In the field of image watermarking technology, achieving a balance between imperceptibility, robustness, and embedding capacity is a key issue. To address this issue, this paper proposes a high-capacity color image adaptive watermarking scheme based on discrete wavelet transform (DWT), Heisenberg decomposition (HD), and singular value decomposition (SVD). In order to enhance the security of the watermark, Logistic chaotic mapping was used to encrypt the watermark image. By adaptively calculating the embedding factor through the entropy of the cover image, and then combining it with Alpha blending technology, the watermark image is embedded into the Y component of the YCbCr color space to enhance the imperceptibility of the algorithm. In addition, the robustness of the algorithm was further improved through singular value correction methods. The experimental results show that the average PSNR and SSIM of the watermarking scheme are 45.3437dB and 0.9987, respectively. When facing various attacks, the average NCC of the extracted watermark reaches above 0.95, indicating good robustness. The embedding capacity of this scheme is 0.6667bpp, which is higher than other watermarking schemes, and the average running time is 1.1136 seconds, which is better than most schemes.

Adaptive Robust Watermarking for Resisting Multiple Distortions in Real Scenes

Adaptive Robust Watermarking for Resisting Multiple Distortions in Real Scenes

Novel optimal region based robust watermarking using modified dragonfly optimization algorithm

Novel optimal region based robust watermarking using modified dragonfly optimization algorithm