Watermark Removal Research Articles

A unified noise and watermark removal from information Bottleneck-based modeling

Both image denoising and watermark removal aim to restore a clean image from an observed noisy or watermarked one. The past research consists of the non-learning type with limited effectiveness or the learning types with limited interpretability. To address these issues simultaneously, we propose a method to deal with both the image-denoising and watermark removal tasks in a unified approach. The noises and watermarks are both considered to have different nuisance patterns from the original image content, therefore should be detected by robust image analysis. The unified detection method is based on the well-known information bottleneck (IB) theory and the proposed SIB-GAN where image content and nuisance patterns are well separated by a supervised approach. The IB theory guides us to keep the valuable content such as the original image by a controlled compression on the input (the noisy or watermark-included image) and then only the content without the nuisances can go through the network for effective noise or watermark removal. Additionally, we adjust the compression parameter in IB theory to learn a representation that approaches the minimal sufficient representation of the image content. In particular, to deal with the non-blind noises, an appropriate amount of compression can be estimated from the solid theory foundation. Working on the denoising task given the unseen data with blind noises also shows the model’s generalization power. All of the above shows the interpretability of the proposed method. Overall, the proposed method has achieved promising results across three tasks: image denoising, watermark removal, and mixed noise and watermark removal, obtaining resultant images very close to the original image content and owning superior performance to almost all state-of-the-art approachesthat deal with the same tasks.

Social Media Authentication and Combating Deepfakes using Semi-fragile Invisible Image Watermarking

With the significant advances in deep generative models for image and video synthesis, Deepfakes and manipulated media have raised severe societal concerns. Conventional machine learning classifiers for deepfake detection often fail to cope with evolving deepfake generation technology and are susceptible to adversarial attacks. Alternatively, invisible image watermarking is being researched as a proactive defense technique that allows media authentication by verifying an invisible secret message embedded in the image pixels. A handful of invisible image watermarking techniques introduced for media authentication have proven vulnerable to basic image processing operations and watermark removal attacks. In response, we have proposed a semi-fragile image watermarking technique that embeds an invisible secret message into real images for media authentication. Our proposed watermarking framework is designed to be fragile to facial manipulations or tampering while being robust to benign image-processing operations and watermark removal attacks. This is facilitated through a unique architecture of our proposed technique consisting of critic and adversarial networks that enforce high image quality and resiliency to watermark removal efforts, respectively, along with the backbone encoder-decoder and the discriminator networks. This allows images shared over the Internet to retain the verifiable watermark as long as facial manipulations or any other Deepfake modification technique is not applied. Thorough experimental investigations on SOTA facial Deepfake datasets demonstrate that our proposed model can embed a \(64\) -bit secret as an imperceptible image watermark that can be recovered with a high-bit recovery accuracy when benign image processing operations are applied while being non-recoverable when unseen Deepfake manipulations are applied. In addition, our proposed watermarking technique demonstrates high resilience to several white-box and black-box watermark removal attacks. Thus, obtaining state-of-the-art performance.

Perceptive Self-Supervised Learning Network for Noisy Image Watermark Removal

Perceptive Self-Supervised Learning Network for Noisy Image Watermark Removal

A Self-Supervised CNN for Image Watermark Removal

A Self-Supervised CNN for Image Watermark Removal

An Overview of TheProposed Technique for Removing Visible Watermark

Watermarks are commonly used to protect the ownership and copyright of digital media. However, there are legitimate scenarios where watermark removal is necessary. Recent advancements in deep learning have led to the development of sophisticated techniques for both detecting and removing watermarks.this research provides a summary of methods for detecting and removing Regenerative AdversarialNetworks (GANs) are one noteworthy method. It is possible to train GANs to recognize watermark patterns and produce unwatermarked versions of watermarked content. One such method, which uses GANs to find and remove watermarks in deep neural networks (DNNs), has been demonstrated to be successful even when it comes to DNN watermarks that are based on backdoors.Another method makes use of deep neural networks' U-structure, which is highly effective in translating images. A comprehensive model like the AdvancedUnet has been developed to concurrently extract and remove visual watermarks. This model uses a deep-supervised hybrid loss to direct the network in learning the transformation between the watermarked input and the clean ground truth. It also integrates efficient modules to extend the architecture's depth without appreciably increasing computingcosts.

Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal

Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Visible watermark removal aims to eliminate the interference of watermarks and restore the background content. However, existing methods often implement watermark component removal and background restoration tasks within a singular branch, leading to residual watermarks in the predictions and ignoring cases where watermarks heavily obscure the background. To address these limitations, this study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks and peripheral contextual information from unaffected regions. Moreover, a Global and Local Context Interaction module is built upon multi-layer perceptrons and bidirectional feature transformation for comprehensive representation modeling in the background restoration phase. The efficacy of our approach is empirically validated across two large-scale datasets, and our findings reveal a marked enhancement over existing watermark removal techniques.

Adversarial watermark: A robust and reliable watermark against removal

Digital image watermarking used to be an important tool for copyright protection. However, as neural network-based watermark removal methods have been proposed in recent years, the embedded watermark is increasingly easy to be erased, which poses a great threat to copyright protection. To address this issue, we propose an adversarial visible watermark scheme, which combines the visible watermark with the adversarial perturbation. By attacking the watermark removal network, we maximize the resistance of visible watermark against removal while minimizing the visual distortion. To further improve the robustness against various transformations (e.g. cropping, JPEG compression), we employ the region of interest and random pre-processing to embed the adversarial visible watermark. The experimental results show that the proposed scheme can effectively resist the removal of watermarks on different datasets and network structures while having good transferability and robustness, which enables the watermark to continue to be an effective copyright protection method.

Two-Stage Watermark Removal Framework for Spread Spectrum Watermarking

Two-Stage Watermark Removal Framework for Spread Spectrum Watermarking

Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooring

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 a 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 article, we propose a novel client-side FL watermarking scheme to tackle the copyright protection issue in secure FL with HE. To the best of our knowledge, it is the first scheme to embed the watermark to models under a secure FL environment. We design a black-box watermarking scheme based on client-side backdooring to embed a pre-designed trigger set into an FL model by a gradient-enhanced embedding method. Additionally, we propose a trigger set construction mechanism to ensure that the watermark cannot be forged. Experimental results demonstrate that our proposed scheme delivers outstanding protection performance and robustness against various watermark removal attacks and ambiguity attack.

DENet: Disentangled Embedding Network for Visible Watermark Removal

Adding visible watermark into image is a common copyright protection method of medias. Meanwhile, public research on watermark removal can be utilized as an adversarial technology to help the further development of watermarking. Existing watermark removal methods mainly adopt multi-task learning networks, which locate the watermark and restore the background simultaneously. However, these approaches view the task as an image-to-image reconstruction problem, where they only impose supervision after the final output, making the high-level semantic features shared between different tasks. To this end, inspired by the two-stage coarse-refinement network, we propose a novel contrastive learning mechanism to disentangle the high-level embedding semantic information of the images and watermarks, driving the respective network branch more oriented. Specifically, the proposed mechanism is leveraged for watermark image decomposition, which aims to decouple the clean image and watermark hints in the high-level embedding space. This can guarantee the learning representation of the restored image enjoy more task-specific cues. In addition, we introduce a self-attention-based enhancement module, which promotes the network's ability to capture semantic information among different regions, leading to further improvement on the contrastive learning mechanism. To validate the effectiveness of our proposed method, extensive experiments are conducted on different challenging benchmarks. Experimental evaluations show that our approach can achieve state-of-the-art performance and yield high-quality images. The code is available at: https://github.com/lianchengmingjue/DENet.

Adaptive Reversible Visible Watermarking Based on Total Variation for BTC-Compressed Images

Few previous Reversible Visible Watermarking (RVW) schemes have both good transparency and watermark visibility. An adaptive RVW scheme that integrates Total Variation and visual perception in Block Truncation Coding (BTC) compressed domain, called TVB-RVW is proposed in this paper. A new mean image estimation method for BTC-compressed images is first developed with the help of Total Variation. Then, a visual perception factor computation model is devised by fusing texture and luminance characteristics. An adaptive watermark embedding strategy is used to embed the visible watermark with the effect of the visual perception factor in the BTC domain. Moreover, a lossless embedding method of the encrypted visible watermark is exploited to deter illegal watermark removal. The visible watermark can be removed since the visual perception factor and the estimated mean image remain unchanged before and after watermark embedding. Extensive experiments validate the superiority of the proposed algorithm over previous RVW schemes in BTC in terms of the visual quality of watermarked images and watermark visibility, and it can achieve a good balance between transparency and watermark visibility.

An Improved U-Net for Watermark Removal

Convolutional neural networks (CNNs) with different layers have performed with excellent results in watermark removal. However, how to extract robust and effective features via CNNs of black box in watermark removal is very important. In this paper, we propose an improved watermark removal U-net (IWRU-net). Taking the robustness of obtained information into account, a serial architecture is designed to facilitate useful information for guaranteeing performance in watermark removal. Taking the problem of long-term dependency into account, U-nets based simple components are integrated into the serial architecture to extract more salient hierarchical information for addressing watermark removal problems. To increase the adaptability of IWRU-net to the real world, we use randomly distributed blind watermarks to implement a blind watermark removal model. The experiment results illustrate that the proposed method is superior to other popular watermark removal methods in terms of quantitative and qualitative evaluations.

Interactive image manipulation using morphological trees and spline-based skeletons

The ability to edit an image using intuitive commands and primitives is a desired feature for any image editing software. In this paper, we combine recent results in medial axes with the well-established morphological tree representations to develop an interactive image editing tool that provides global and local image manipulation using high-level primitives. We propose a new way to render interactive morphological trees using icicle plots and introduce different ways of manipulating spline-based medial axis transforms for grayscale and colored image editing. Different applications of the tool, such as watermark removal, image deformation, dataset augmentation for machine learning, artistic illumination manipulation, image rearrangement, and clothing design, are described and showcased on examples.

An image watermark removal method for secure internet of things applications based on federated learning

AbstractWatermark adding is one of the important means for image security and privacy protection in Internet of things (IOT) applications based on federated learning. It is often inseparable from adversarial training with watermark removal algorithms. The effect of watermark removal algorithms will directly affect the final result of watermark addition. However, the existing watermark removal algorithms have drawbacks such as incomplete image watermark removal, poor image quality after watermark removal, large demand for training data, and incorrect filling, which seriously affects the development of image information security and privacy protection in IOT applications based on federated learning. To solve the above problems, this paper proposes an improved image watermark removal convolutional network model based on deep image prior. First, we improve the U‐Net network model, using six downsamping layers and six deconvolution layers combined with deep image prior method to reduce the loss of details and perceive high‐level features, thereby improving the ability of the network to extract high‐level features of the image. In addition, we design a new type of loss function which is called stair loss, and add L1 loss and perception loss to establish new constraints. In order to verify the effectiveness of our method, a comprehensive experimental comparison was conducted on the public dataset PASCAL VOC 2012 in the same experimental environment with CGAN and the deep prior method. The experimental results show that the improved model combined with the deep image prior method can extract the high‐level feature information and can directly remove the watermark from the picture without pretraining the network, the L1 loss and perceptual loss can better retain the image structure information and speed up the watermark removal of the model, the stair loss corrects the final output more accurately by correcting the output of each layer; our method improves the learning ability of the model, and under the condition of the same training time, the image quality after watermark removal is higher, and the final watermark removal result is better, which is more suitable for distributed structure of IoT application based on federated learning.

Survey on deep learning applications in digital image security

In the digital era, sharing pictures on social media has become a common privacy issue. To prevent private images from being eavesdropped on and destroyed, developing secure and efficient image steganography, image cryptography, and image authentication has been difficult. Deep learning provides a solution for digital image security. First, we make an overall conclusion on deep learning applications in image steganography to generate five aspects: the cover image, stego-image, embedding change probabilities, coverless steganography, and steganalysis. Second, we also combine and compare deep learning methods used in six aspects: image cryptography from image compression, image resolution improvement, image object detection and classification, key generation, end-to-end image encryption, and image cryptoanalysis. Third, we collect deep learning methods in image authentication from five perspectives: image forgery detection, watermarked image generation, image watermark extraction and detection, image watermarking attack, and image watermark removal. Finally, we summarize future research directions of deep learning utilization in image steganography, image cryptography, and image authentication.

WATERMARK TECHNIQUE FOR AUTHENTICATION OF VISIBLY WATERMARK IMAGES

With the rapid spread of computer networks and the wide use of multimedia technologies, many watermarking techniques are now under development and investigation for protecting owner's intellectual rights. Watermarks can be divided into two types, visible and invisible watermarks, physical visible watermarks have been used for centuries. Now days it is used in digital library, in video broad casting, and other multimedia services. The visible watermark may face several problems. Among these problems, watermark removal and unauthorized insertion are two main concern. This paper proposes a method of invisible watermark to overcome these problems. The watermarking process based on hiding a selected watermark object, that holds a little a mount of information relative to the source object, inside the cover image which has to be authenticated. The processes are based on using invisible watermarks to protect visibly watermarked images which are done by using different techniques. The experiments have shown that the proposed algorithm can provide a very effective protection for watermarked images.

Frequency Domain for Color Image Authentication Proofing

Digital watermarking is the process of embedding data known as a watermark into a multimedia object so that the watermark can later be identified or recovered to claim its object. The use of an embedded watermark would enable the owner of the work hardware to be identified. In the proposed method the Particle-Swarm-Optimization (PSO) algorithm has been applied to embed a binary watermark bit in the optimal color sub-bands, resulting in a less extreme value after the PSO point. The embedding level, which uses Discrete Wavelet Transform (DWT) to embed binary bits in the resulted image in the low-frequency domain, must be able to withstand intended attacks while maintaining high quality, as well as assess image authentication and localize tampering areas (s). Various consistency metrics and watermark removal attacks are used to evaluate the algorithm in an experimental environment. The results show that the model can support imperceptible watermarking as well as high attack resistance.

Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal

Digital watermark is a commonly used technique to protect the copyright of medias. Simultaneously, to increase the robustness of watermark, attacking technique, such as watermark removal, also gets the attention from the community. Previous watermark removal methods require to gain the watermark location from users or train a multi-task network to recover the background indiscriminately. However, when jointly learning, the network performs better on watermark detection than recovering the texture. Inspired by this observation and to erase the visible watermarks blindly, we propose a novel two-stage framework with a stacked attention-guided ResUNets to simulate the process of detection, removal and refinement. In the first stage, we design a multi-task network called SplitNet. It learns the basis features for three sub-tasks altogether while the task-specific features separately use multiple channel attentions. Then, with the predicted mask and coarser restored image, we design RefineNet to smooth the watermarked region with a mask-guided spatial attention. Besides network structure, the proposed algorithm also combines multiple perceptual losses for better quality both visually and numerically. We extensively evaluate our algorithm over four different datasets under various settings and the experiments show that our approach outperforms other state-of-the-art methods by a large margin.

Seam Carving based visible watermarking robust to removal attacks

Visible watermarking offers direct copyright protection to the naked eye using visible pattern superimposed in the host image. However, due to their exposure, the watermark pattern becomes an easy target to remove by malicious entities that generates copyright-free images. Until now, in the scientific literature several semi-automatic visible watermark removal attacks have been proposed, showing enough visual quality of the recovered host image. In this paper, we propose a watermark design based on modified Seam Carving technique to provide robustness against removal attacks including inpainting-based attacks, Independent Component Analysis (ICA)-based attacks, and image matting-based attacks. Robustness against the attacks is measured using common image quality assessments and a watermark visibility assessment based on the Human Visual System (HVS). Experimental results show robustness of the proposed method against above mentioned watermark removal attacks under the most severe situation, in which adversary has the logotype used as a watermark pattern because it is public in Internet. The proposed method can be applied to any visible watermarking algorithms to make them robust against illegal removal attempts, without sacrificing their original functionality, such as reversibility for authorized users.

Simultaneous speaker identification and watermarking

Biometric template protection of speech signals and information hiding in speech signals are two challenging issues. To resolve such limitations and increase the level of security, our objective is to build multi-level security systems based on speech signals. So, speech watermarking is used simultaneously with automatic speaker identification. The speech watermarking is performed to embed images into the speech signals that are used for speaker identification. The watermark is extracted for authentication, and then the effect of watermark removal on the performance of the speaker identification system in the presence of degradations is studied. This paper presents an approach for speech watermarking based on empirical mode decomposition (EMD) in different transform domains and singular value decomposition (SVD). The speech signal is decomposed in different transform domains with EMD to yield zero-mean components called intrinsic mode functions (IMFs). The watermark is inserted into one of these IMF components with SVD. A comparison between different transform domains for implementing the proposed watermarking scheme on different IMFs is presented. The log-likelihood ratio (LLR), correlation coefficient (Cr), signal-to-noise ratio (SNR), and spectral distortion (SD) are used as metrics for the comparison. According to the simulation results, we find that the watermark embedding in the discrete sine transform domain provides higher SNR and Cr values and lower SD and LLR values. The proposed approach is robust to different attacks.