Search Results (384)

The rapid advancement of AI-generated content (AIGC) has significantly improved the realism and accessibility of synthetic images. While large image generation models offer immense potential in creative industries, they also introduce serious challenges, including copyright infringement, content authentication, and the traceability of generated images. Digital watermarking has emerged as a promising approach to address these concerns by embedding imperceptible yet detectable signatures into generated images. This survey provides a comprehensive review of three core areas: (1) the evolution of image generation technologies, highlighting key milestones such as the transition from GANs to diffusion models; (2) traditional and state-of-the-art digital image watermarking algorithms, encompassing spatial domain, transform domain, and deep learning-based approaches; (3) watermarking methods specific to AIGC, including ownership authentication of AI model and diffusion model, and watermarking of AI-generated images. Additionally, we examine common performance evaluation metrics used in this field, such as watermark capacity, watermark detection accuracy, fidelity, and robustness. Finally, we discuss the unresolved issues and propose several potential directions for future research. We look forward to this paper offering valuable reference for academics in the field of AIGC watermarking and related fields. Full article

With the increasing amount of cloud-based speech files, the privacy protection of speech files faces significant challenges. Therefore, integrity authentication of speech files is crucial, and there are two pivotal problems: (1) how to achieve fine-grained and highly accurate tampering detection and (2) how to perform high-quality tampering recovery under high tampering ratios. Tampering detection methods and tampering recovery methods of existing speech integrity authentication are mutually balanced, and most tampering recovery methods are carried out under ideal tampering conditions. This paper proposes an encrypted speech integrity authentication method that can simultaneously address both of problems, and its main contributions are as follows: (1) A 2-least significant bit (2-LSB)-based dual fragile watermarking method is proposed to improve tampering detection performance. This method constructs correlations between encrypted speech sampling points by 2-LSB-based fragile watermarking embedding method and achieves low-error tampering detection of tampered sampling points based on four types of fragile watermarkings. (2) A speech self-recovery model based on residual recovery-based linear interpolation (R2-Lerp) is proposed to achieve tampering recovery under high tampering ratios. This method constructs the model based on the correlation between tampered sampling points and their surrounding sampling points and refines the scenarios of the model according to the tampering situation of the sampling points, with experimental results showing that the recovered speech exhibits improved auditory quality and intelligibility. (3) A scrambling encryption algorithm based on the Lorenz mapping is proposed as the speech encryption method. This method scrambles the speech sampling points several times through 4-dimensional chaotic sequence, with experimental results showing that this method not only ensures security but also slightly improves the effect of tampering recovery. Full article

This study presents a ring template watermarking method utilizing semantic segmentation and elliptical fitting to address the inadequate resilience of digital watermarking techniques for remote sensing images against geometric attacks and affine transformations. The approach employs a convolutional neural network to determine the coverage position of the annular template watermark automatically. Subsequently, it applies the least squares approach to align with the relevant elliptic curve of the annular watermark, facilitating the restoration of the watermark template post-deformation due to an attack. Ultimately, it acquires the watermark information by analyzing the binarized image according to the coordinates. The experimental results indicate that, despite various geometric and affine modification attacks, the NC mean value of watermark extraction exceeds 0.83, and the PSNR value surpasses 35, thereby ensuring substantial invisibility and enhanced robustness. In addition, the methods presented in this paper provide useful references for imaging data in other fields. Full article

To address the variability and complexity of attack types, this paper proposes a multi-instance zero-watermarking algorithm that goes beyond the conventional one-to-one watermarking approach. Inspired by the class-instance paradigm in object-oriented programming, this algorithm constructs multiple zero watermarks from a single vector geographic dataset to enhance resilience against diverse attacks. Normalization is applied to eliminate dimensional and deformation inconsistencies, ensuring robustness against non-uniform scaling attacks. Feature triangle construction and angle selection are further utilized to provide resistance to interpolation and compression attacks. Moreover, angular features confer robustness against translation, uniform scaling, and rotation attacks. Experimental results demonstrate the superior robustness of the proposed algorithm, with normalized correlation values consistently maintaining 1.00 across various attack scenarios. Compared with existing methods, the algorithm exhibits superior comprehensive robustness, effectively safeguarding the copyright of vector geographic data. Full article

Deep learning-based remote sensing object detection (RSOD) models have been widely deployed and commercialized. The commercialization of RSOD models requires the ability to protect their intellectual property (IP) across different platforms and sales channels. However, RSOD models currently face threats related to illegal copying on untrusted platforms or resale by dishonest buyers. To address this issue, we propose a dual-model watermarking scheme for the copyright verification and leakage tracing of RSOD models. First, we construct trigger samples using an object generation watermark trigger and train them alongside clean samples to implement black-box watermarking. Then, fingerprint information is embedded into a small subset of the model’s critical weights, using a fine-tuning and loss-guided approach. At the copyright verification stage, the presence of a black-box watermark can be confirmed through using the suspect model’s API to make predictions on the trigger samples, thereby determining whether the model is infringing. Once infringement is confirmed, fingerprint information can be further extracted from the model weights to identify the leakage source. Experimental results demonstrate that the proposed method can effectively achieve the copyright verification and traceability of RSOD models without affecting the performance of primary tasks. The watermark shows good robustness against fine-tuning and pruning attacks. Full article

Combining blockchain technology with digital watermarking presents an efficient solution for safeguarding vector map files. However, the large data volume and stringent confidentiality requirements of vector maps pose significant challenges for direct registration on blockchain platforms. To overcome these limitations, this paper proposes a blockchain-based copyright protection model utilizing unique identifiers (BCPM-UI). The model employs a distance ratio-based quantization watermarking algorithm to embed watermark information into vector maps and then generates unique identifiers based on their topological and geometric parameters. These identifiers, rather than the vector maps themselves, are securely registered on the blockchain. To ensure reliable copyright verification, a bit error rate (BER)-based matching algorithm is introduced, enabling accurate comparison between the unique identifiers of suspected infringing data and those stored on the blockchain. Experimental results validate the model’s effectiveness, demonstrating the high uniqueness and robustness of the identifiers generated. Additionally, the proposed approach reduces blockchain storage requirements for map data by a factor of 200, thereby meeting confidentiality standards while maintaining practical applicability in terms of copyright protection for vector maps. Full article

Federated learning consists of a central aggregator and multiple clients, forming a distributed structure that effectively protects data privacy. However, since all participants can access the global model, the risk of model leakage increases, especially when unreliable participants are involved. To safeguard model copyright while enhancing the robustness and secrecy of the watermark, this paper proposes a client-side watermarking scheme. Specifically, the proposed method introduces an additional watermark class, expanding the output layer of the client model into an $N+1$-class classifier. The client’s local model is then trained using both the watermark dataset and the local dataset. Notably, before uploading to the server, the parameters of the watermark class are removed from the output layer and stored locally. Additionally, the client uploads amplified parameters to address the potential weakening of the watermark during the aggregation. After aggregation, the global model is distributed to the clients for local training. Through multiple rounds of iteration, the saved watermark parameters are continuously updated until the global model converges. On the MNIST, CIFAR-100, and CIFAR-10 datasets, the watermark detection rates on VGG-16 and ResNet-18 reached 100%. Furthermore, extensive experiments demonstrate that this method has minimal impact on model performance and exhibits strong robustness against pruning and fine-tuning attacks. Full article

Watermarking is a technique used to address issues related to the widespread use of the internet, such as copyright protection, tamper localization, and authentication. However, most watermarking approaches negatively affect the quality of the original image. In this research, we propose an optimized image watermarking approach that utilizes the dual-tree complex wavelet transform and particle swarm optimization algorithm. Our approach focuses on maintaining the highest possible quality of the watermarked image by minimizing any noticeable changes. During the embedding phase, we break down the original image using a technique called dual-tree complex wavelet transform (DTCWT) and then use particle swarm optimization (PSO) to choose specific coefficients. We embed the bits of a binary logo into the least significant bits of these selected coefficients, creating the watermarked image. To extract the watermark, we reverse the embedding process by first decomposing both versions of the input image using DTCWT and extracting the same coefficients to retrieve those corresponding bits (watermark). In our experiments, we used a common dataset from watermarking research to demonstrate the functionality against various watermarked copies and peak signal-to-noise ratio (PSNR) and normalized cross-correlation (NCC) metrics. The PSNR is a measure of how well the watermarked image maintains its original quality, and the NCC reflects how accurately the watermark can be extracted. Our method gives mean PSNR and NCC of 80.50% and 92.51%, respectively. Full article

The modern society generates vast amounts of digital content, whose credibility plays a pivotal role in shaping public opinion and decision-making processes. The rapid development of social networks and generative technologies, such as deepfakes, significantly increases the risk of disinformation through image manipulation. This article aims to review methods for verifying images’ integrity, particularly through deep learning techniques, addressing both passive and active approaches. Their effectiveness in various scenarios has been analyzed, highlighting their advantages and limitations. This study reviews the scientific literature and research findings, focusing on techniques that detect image manipulations and localize areas of tampering, utilizing both statistical properties of images and embedded hidden watermarks. Passive methods, based on analyzing the image itself, are versatile and can be applied across a broad range of cases; however, their effectiveness depends on the complexity of the modifications and the characteristics of the image. Active methods, which involve embedding additional information into the image, offer precise detection and localization of changes but require complete control over creating and distributing visual materials. Both approaches have their applications depending on the context and available resources. In the future, a key challenge remains the development of methods resistant to advanced manipulations generated by diffusion models and further leveraging innovations in deep learning to protect the integrity of visual content. Full article

Pre-trained language models such as BERT, GPT-3, and T5 have made significant advancements in natural language processing (NLP). However, their widespread adoption raises concerns about intellectual property (IP) protection, as unauthorized use can undermine innovation. Watermarking has emerged as a promising solution for model ownership verification, but its application to NLP models presents unique challenges, particularly in ensuring robustness against fine-tuning and preventing interference with downstream tasks. This paper presents a novel watermarking scheme, TIBW (Task-Independent Backdoor Watermarking), that embeds robust, task-independent backdoor watermarks into pre-trained language models. By implementing a Trigger–Target Word Pair Search Algorithm that selects trigger–target word pairs with maximal semantic dissimilarity, our approach ensures that the watermark remains effective even after extensive fine-tuning. Additionally, we introduce Parameter Relationship Embedding (PRE) to subtly modify the model’s embedding layer, reinforcing the association between trigger and target words without degrading the model performance. We also design a comprehensive watermark verification process that evaluates task behavior consistency, quantified by the Watermark Embedding Success Rate (WESR). Our experiments across five benchmark NLP tasks demonstrate that the proposed watermarking method maintains a near-baseline performance on clean inputs while achieving a high WESR, outperforming existing baselines in both robustness and stealthiness. Furthermore, the watermark persists reliably even after additional fine-tuning, highlighting its resilience against potential watermark removal attempts. This work provides a secure and reliable IP protection mechanism for NLP models, ensuring watermark integrity across diverse applications. Full article

In recent years, the internet has developed rapidly. With the popularity of social media, uploading and backing up digital images has become the norm. A huge number of digital images are circulating on the internet daily, and issues related to information security follow. To protect intellectual property rights, digital watermarking is an indispensable technology. However, the common lossy compression technology in the network transmission process is a big problem for watermarking. This paper describes an innovative semi-blind watermarking method with the use of deep convolutional generative adversarial networks (DCGANs) for hiding and extracting watermarks from JPEG-compressed images. The proposed method achieves an average peak signal-to-noise ratio (PSNR) of 49.99 dB, a structural similarity index (SSIM) of 0.95, and a bit error rate (BER) of 0.008 across varying JPEG quality factors. The process is based on an embedder, decoder, generator, and discriminator. It allows watermarking, decoding, or reconstruction to be symmetric such that there is less distortion and durability is improved. It constructs a specific generator for each image and watermark that is supposed to be protected. Experimental results show that, with the variety of JPEG quality factors, the restored watermark achieves a remarkably low corrupted rate, outstripping recent deep learning-based watermarking methods. Full article

The widespread distribution of medical images in smart healthcare systems will cause privacy concerns. The unauthorized sharing of decrypted medical images remains uncontrollable, though image encryption can discourage privacy disclosure. This research proposes a double-level security scheme for medical images to overcome this problem. The proposed joint encryption and watermarking scheme is based on singular-value decomposition (SVD) and chaotic maps. First, three different random sequences are used to encrypt the LL subband in the discrete wavelet transform (DWT) domain; then, HL and LH sub-bands are embedded with watermark information; in the end, we obtain the watermarked and encrypted image with the inverse DWT (IDWT) transform. In this study, SVD is used for watermarking and encryption in the DWT domain. The main originality is that decryption and watermark extraction can be performed separately. Experimental results demonstrate the superiority of the proposed method in key spaces (${10}^{225}$), PSNR (76.2543), and UACI (0.3329). In this implementation, the following key achievements are attained. First, our scheme can meet requests of different security levels. Second, encryption and watermarking can be performed separately. Third, the watermark can be detected in the encrypted domain. Thus, experiment results and security analysis demonstrate the effectiveness of the proposed scheme. Full article

To guarantee the reliability and integrity of audio, data have been focused on as an essential topic as the fast development of generative AI. Significant progress in machine learning and speech synthesis has increased the potential for audio tampering. In this paper, we focus on the digital watermarking method as a promising method to safeguard the authenticity of audio evidence. Due to the integrity of the original data with probative importance, the algorithm requires reversibility, imperceptibility, and reliability. To meet the requirements, we propose a reversible digital watermarking approach that embeds feature data concentrating in high-frequency intDCT coefficients after transforming data from the time domain into the frequency domain. We explored the appropriate hiding locations against spectrum-based attacks with novel proposed methodologies for spectral expansion for embedding. However, the drawback of fixed expansion is that the stego signal is prone to being detected by a spectral analysis. Therefore, this paper proposes two other new expansion methodologies that embed the data into variable locations—random expansion and adaptive expansion with distortion estimation for embedding—which effectively conceal the watermark’s presence while maintaining high perceptual quality with an average segSNR better than 21.363 dB and average MOS value better than 4.085. Our experimental results demonstrate the efficacy of our proposed method in both sound quality preservation and log-likelihood value, indicating the absolute discontinuity of the spectrogram after embedding is proposed to evaluate the effectiveness of the proposed reversible spectral expansion watermarking algorithm. The result of EER indicated that the adaptive hiding performed best against attacks by spectral analysis. Full article

The integration of Internet of Medical Things (IoMT) technology has revolutionized healthcare, allowing rapid access to medical images and enhancing remote diagnostics in telemedicine. However, this advancement raises serious cybersecurity concerns, particularly regarding unauthorized access and data integrity. This paper presents a novel, user-friendly, visible watermarking scheme for medical images—Visual and User-Friendly Medical Image Watermarking Scheme (VUF-MIWS)—designed to secure medical image ownership while maintaining usability for diagnostic purposes. VUF-MIWS employs a unique combination of inpainting and data hiding techniques to embed hospital logos as visible watermarks, which can be removed seamlessly once image authenticity is verified, restoring the image to its original state. Experimental results demonstrate the scheme’s robust performance, with the watermarking process preserving critical diagnostic information with high fidelity. The method achieved Peak Signal-to-Noise Ratios (PSNR) above 70 dB and Structural Similarity Index Measures (SSIM) of 0.99 for inpainted images, indicating minimal loss of image quality. Additionally, VUF-MIWS effectively restored the ROI region of medical images post-watermark removal, as verified through test cases with restored watermarked regions matching the original images. These findings affirm VUF-MIWS’s suitability for secure telemedicine applications. Full article

With the rapid digitization of healthcare, the secure transmission of medical images has become a critical concern, especially given the increasing prevalence of cyber threats and data privacy breaches. Medical images are frequently transmitted via the Internet and cloud platforms, making them susceptible to unauthorized access, tampering, and theft. While traditional cryptographic techniques play a vital role, they are often insufficient to fully ensure the integrity and confidentiality of these sensitive images. In this paper, we present AGFI-GAN, a robust and secure framework for medical image watermarking that leverages attention-guided and Feature-Integrated mechanisms within a Generative Adversarial Network (GAN). Specifically, a Feature-Integrated Module (FIM) is proposed to effectively capture and combine both shallow and deep image features to facilitate multilayer fusion with the watermark. The dense connections within the module facilitate feature reuse, boosting the system’s robustness. To mitigate distortion from watermark embedding, an Attention Module (AM) is utilized, generating an attention mask by extracting global image features. This attention mask prioritizes features in less prominent and textured regions, allowing for stronger watermark embedding, while other features are downplayed to enhance the overall effectiveness of the watermarking process. The framework is evaluated based on its versatility, embedding capacity, robustness, and imperceptibility, and the results confirm its effectiveness. The study shows a marked improvement over the baseline, thus highlighting the framework’s superiority. Full article