Generative steganography has recently attracted considerable attention due to its superior security properties. However, most existing approaches suffer from limited hiding capacity. To address this issue, this paper proposes a high-capacity image steganography framework that integrates an encoder–decoder architecture with a latent diffusion model. Specifically, a message encoder is designed to transform binary secret messages into latent-space representations through a series of ResDense modules, enabling efficient hiding of large-scale information. The encoded latent features are then guided by the latent diffusion model to synthesize visually realistic stego images. During message extraction, the stego image undergoes iterative noise addition within the diffusion process to reconstruct the latent representation, from which a message decoder accurately recovers the hidden message. Extensive experimental results demonstrate that the proposed method achieves a high hiding capacity of over 30,000 bits, outperforming state-of-the-art methods while ensuring reliable message recovery under common image storage formats such as JPEG and PNG.

Robust audio fingerprinting plays a crucial role in applications such as audio authentication and copyright protection. However, existing fingerprinting techniques often rely heavily on hand-crafted features and struggle to maintain robustness and generalization, particularly when dealing with long-duration audios and facing complex distortions. To address these challenges, we propose a deep learning framework for robust audio fingerprinting with multi-feature enhancement. First, origin audio is transformed into Log-Mel spectrum, and time-frequency features are extracted by a convolutional neural network (CNN). Then, we apply a dual-domain attention module with a dimension reduction component to dynamically capture salient regions in both time and frequency domains. Finally, we use metric learning to optimize the fingerprint space, ensuring better separation between positive and negative samples. Experimental results show that our method achieves an AUC of 0.99 on ROC curves, outperforming typical methods by up to 5.3%, with particularly strong robustness under distortions including background noise, time scaling and sampling rate changes.

Asymmetric numeral systems (ANS) is a widely used entropy coding method in commercial compressors due to its high performance. Joint compression and encryption techniques can offer reliability and cost-effectiveness for secure Big Data storage. However, existing joint compression-encryption schemes for ANS coding often suffer from either increased storage space requirements or limited security. To address these issues, this paper proposes two ANS-based joint compression-encryption algorithms that provide considerable security with almost no compression loss. The first scheme, based on interval swapping, employs a cryptographically secure ChaCha20 generator to perturb the order of contiguous intervals, thereby introducing controlled randomness into the encoding process. The second scheme, based on interval splitting, discards the conventional assumption of representing each symbol with a single contiguous interval, instead assigning multiple sub-intervals to enhance both security and flexibility. In addition, a sequence of output permutations is applied to further strengthen resistance against attacks. Experimental results show that the proposed methods reduce compression loss by approximately 3.83% compared with existing schemes, while the interval swapping scheme achieves a 46.9% reduction in time cost. Security analysis confirms that the enlarged key space significantly increases robustness against brute-force attacks. These results demonstrate that the proposed approaches effectively balance compression efficiency and encryption strength, offering a lightweight and secure solution for Big Data storage.

Image steganography, a crucial technique for secure information transmission, faces the challenge of balancing embedding capacity with visual imperceptibility and security. Existing methods often struggle to maximize these metrics simultaneously, particularly when handling complex image details and achieving adaptive feature representation. To address this, we propose EctFormer, a novel deep steganography framework based on Image Hiding Empirical Mode Decomposition (IHEMD). EctFormer employs a compact autoencoder architecture with a key innovation: an integrated IHEMD module that adaptively decomposes images into physically meaningful intrinsic mode functions (IMFs) and residual components. This decomposition allows for superior feature representation and information embedding. Furthermore, we introduce an intrinsic mode loss function within a novel multi-image training strategy, achieving a remarkable embedding capacity of 96 bits per pixel. Experimental results on the DIV2K, COCO, and ImageNet datasets demonstrate EctFormer’s superior performance. Our method significantly improves PSNR (exceeding 17.00 dB for single-image tasks and 11.00 dB for multi-image tasks) while maintaining high SSIM values (above 0.99). These results surpass current state-of-the-art methods, validating the efficacy of our IHEMD-based approach and the proposed training strategy. EctFormer provides a new effective paradigm for image steganography and enables high-capacity, high-security covert communication. The code is available at https://github.com/lisen1129/EctFormer.

Image-in-image hiding, which embeds a full-size secret image into a cover image with minimal perceptual distortion and accurate recovery, has attracted increasing attention because of its wide applications in copyright protection, covert communication, and digital forensics. However, when facing full-size secret images, the secret data often exceed the capacity limitation of individual cover images, resulting in existing solutions struggling to achieve an effective balance among robustness, high load capacity, and resistance to steganalysis and detection capabilities, which is particularly prominent when encountering social noise interference in real-world scenarios. To address these challenges, we propose MambaRIS, a robust and efficient image steganography framework that combines the dual-tree complex wavelet transform (DTCWT) with a state space model. The DTCWT module enables directionally selective decomposition of the input, enriching frequency-domain representations and providing more resilient embedding regions for robust cross-frequency hiding and recovery. Furthermore, we introduce a Mamba-based autoencoder architecture equipped with a novel spatial channel Mamba block (SCMB), which integrates spatial and channel attention mechanisms with linear-time global dependency modeling, significantly improving embedding adaptability under complex noise and distortion conditions. Extensive experiments demonstrate the superiority of the proposed scheme in terms of visual quality, robustness, and resistance to steganalysis. In JPEG compression with a quality factor of Q = 80, our method achieves an average improvement in hiding and recovery accuracy (measured by PSNR) of 0.87 dB compared with state-of-the-art architectures, while reducing the number of parameters by 33%.

With the rapid development of artificial intelligence, deep neural networks (DNN) have become valuable digital assets, thereby highlighting the urgent need for copyright protection and secure transmission. Although traditional model watermarking and active defense techniques offer partial protection against unauthorized use, they often suffer from limited imperceptibility and may degrade model performance. To overcome these challenges, this paper proposes ReFHD-Net, a reversible functionality hiding framework for DNN based on a structured mask matrix. Here, reversible functionality hiding refers to the ability to hide the functionality of secret task within the stego model during transmission and enable its lossless recovery by authorized users at the receiver side. Specifically, ReFHD-Net employs a two-stage strategy to hide the secret functionality within a carrier model. In the first stage, a multi-task learning framework enhanced with homoscedastic uncertainty is employed to jointly train the model on both public and secret tasks. In the second stage, the model parameters are further optimized using a combination of task-driven loss and parameter distribution regularization, which limits parameter deviations caused by the hiding process and enhances the imperceptibility of the secret task. Experimental results on image classification and denoising benchmarks validate the superiority of our ReFHD-Net. It achieves an average degradation of only 0.27% in public task and enables lossless recovery of the secret task with no performance drop. Moreover, our framework exhibits strong robustness and security against various unauthorized recovery attempts including random guessing, fine-tuning, and model pruning.

In recent years, with the rapid advancement of deep neural networks (DNNs), researchers have explored steganography techniques that use DNN models as carriers for secret information hiding. However, existing methods generally suffer from limited imperceptibility and fidelity. To address these limitations, this paper proposes a steganography method that achieves high imperceptibility and fidelity while providing substantial embedding capacity and robustness. Specifically, we introduce a dual-branch encoder that embeds secret information into the initialization parameters of the cover model with almost no degradation of the model’s functionality. In addition, a new SMSE loss is employed to constrain the encoder output, which enhances the imperceptibility of the stego model. After training and transmission, the receiver can utilize a decoder to accurately extract secret information from the stego model. Experimental results demonstrate that the proposed method achieves a Kullback–Leibler (KL) divergence more than an order of magnitude lower than existing methods, with values ranging from 0.0003 to 0.007. The stego model preserves high fidelity to the original model, with classification accuracy differences within 0.005 on benchmark datasets including MNIST, CIFAR-10, and SST-2. In terms of embedding capacity, it achieves 319,312 bits on ResNet-18 and 1,757,952 bits on ViT, which exceeds the performance of baseline methods across most models. Furthermore, the proposed method exhibits strong robustness, as the embedded information can still be accurately recovered with BCH coding even under noise attacks at an SNR as low as -6 dB. It also demonstrates strong generalization, as it performs effectively on both classification networks and generative or reconstruction models such as GANs, VAEs, and U-Nets.

Steganography can be mainly classified into two categories: modification-based and generation-based approaches. Modification-based steganography embeds secret messages by altering specific statistical properties of the cover image, offering relatively high capacity and robustness. However, such modifications also make the stego images more susceptible to be detected by steganalysis tools. In contrast, generation-based steganography, which directly generates them via generative models, provides higher security but suffers from limited hiding capacity and poor robustness. To address these limitations, we propose a unified deep network for image steganography (U-StegNet) that integrates the high capacity and robustness of modification-based steganography with the high security of generation-based steganography. Specifically, we design a dual stage hiding strategy. In the first stage, we utilize a generative model to produce an intermediate image that hides part of the secret message while preserving statistical properties consistent with natural images, thereby enhancing resistance to steganalysis. In the second stage, we design a U-Net-based encoder to hide the remaining secret message into the intermediate image, while simultaneously enhancing fine-grained visual details. Moreover, we introduce a message division module that adaptively allocates the message length for each stage based on the image content and capacity constraints, thereby improving both imperceptibility and robustness. Extensive experimental results demonstrate the effectiveness of our U-StegNet. It achieves a PSNR of 44.41 dB and an SSIM of 0.9968 on stego images, which demonstrates the high imperceptibility of our method. Furthermore, it maintains strong robustness across nine types of common attacks, with message extraction accuracy nearly above 98%.

In this paper, we propose a new decoding algorithm for extremely skewed distribution, so that it can omit reading unnecessary bits and thus improve decoding performance. In particular, the proposed method does not require additional space to store the encoded stream. Specifically, we first reorder the compressed bit sequence as in [1], so that to support direct access without extra space. Then, we propose a labeling method to generate a temporary label corresponding to the encountered block, in order to indicate whether the length of the codeword stored in that block is determined. If it is determined, we can identify where to read the necessary bits for decoding the desired symbol. Otherwise, we read bits from the later blocks to update the labels until the codeword lengths are determined.

Range coding is a type of entropy coding widely used in modern data compressors. However, its compression and decompression processes involve multiple range adjustments, and the bitstream can only be read sequentially during decoding, resulting in quite high latency. In addition, existing input-interleaved fast implementations demand additional computational and memory overhead for the post-compression byte-swizzling step, which leads to increased compression time. In this paper, we propose a parallel range coding method that employs multiple encoders and decoders without the need for the swizzling step. It is achieved by designing a sliding window mechanism to interleave the outputs of multiple encoders, so that the positions of each encoder's outputs in the bitstream follow a predictable and ordered pattern. This design reduces encoding latency and enables each decoder to pre-locate the data it needs to read during decoding, thereby improving both compression and decompression performance. The simulation results indicate that compared to the traditional range coding and existing multi-way input-interleaved implementations (which require a large amount of memory overhead during encoding), our proposal achieves an average throughput increase of 48.03%/81.08% and 74.01%/9.14% during encoding/decoding, respectively, with almost the same compression ratios.

To ensure the security of image information and facilitate efficient management in the cloud, the utilization of reversible data hiding in encrypted images (RDHEIs) has emerged as pivotal. However, most existing RDHEI schemes suffer from lower security and limited embedding capacity. To tackle these challenges, we propose a reversible data hiding (RDH) with secret encrypted image sharing and adaptive coding scheme. Specifically, in the encryption phase, we introduce an improved secret sharing (SS) encryption method based on the Chinese remainder theorem for polynomials (CRTPs). This method not only improves the security of encrypted images but also vacates a larger room for embedding. In the embedding phase, we introduce an adaptive coding embedding approach usingxorpreservation (XORP) and huffman coding, which provides high embedding capacity. Experimental results and security analysis demonstrate that our proposed encryption method achieves optimal values in security indicators for encrypted images, such as information entropy, histograms, number of pixels change rate and unified average changing intensity. The proposed embedding method is superior to some state-of-the-art schemes in terms of embedding capacity. Furthermore, in datasets BOSSBase and BOWS2, the average embedding rates of the proposed embedding approach can reach 2.1745 bits per pixel (bpp) and 2.0656 bpp, respectively.

In today’s intelligent transportation systems, the effectiveness of image-based analysis relies heavily on image quality. To enhance images while preserving reversibility, this article proposes a histogram matching-based reversible data hiding (HMRDH) method. The proposed approach ensures high-embedding capacity by incorporating histogram shifting from reversible data hiding with contrast enhancement (RDHCE). Unlike traditional RDHCE methods that are limited to achieving histogram equalization, our method constrains the sequence of bin adjustments to achieve flexible histogram matching. The algorithm first evaluates bin heights to assign roles, then iteratively selects and adjusts corresponding bins while embedding information. To prevent deviation from the target histogram, this method calculates the root mean square error after each iteration to ensure that the adjustment is retained only if it improves the matching accuracy. When necessary, the original image and embedded information can be fully recovered. Extensive experiments demonstrate the superiority of the proposed method in visual quality, embedding capacity, and adaptability.

To enhance information security during transmission over public channels, images are frequently employed for binary data hiding. Nonetheless, data are vulnerable to distortion due to Joint Photographic Experts Group (JPEG) compression, leading to challenges in recovering the original binary data. Addressing this issue, this paper introduces a pioneering method for binary data hiding that leverages a combined spatial and channel attention Transformer, termed SCFformer, to withstand JPEG compression. This method employs a novel discrete cosine transform (DCT) quantization truncation mechanism during the hiding phase to bolster the stego image’s resistance to JPEG compression, using spatial and channel attention to conceal information in less perceptible areas, thereby enhancing the model’s resistance to steganalysis. In the extraction phase, the DCT quantization minimizes secret image loss during compression, facilitating easier information retrieval. The incorporation of scalable modules adds flexibility, allowing for variable-capacity data hiding. Experimental findings validate the high security, large capacity, and high flexibility of our scheme, alongside a marked improvement in binary data recovery post-JPEG compression, underscoring our method’s leading-edge performance.

This paper proposes an end-to-end two-branch network for a document image perceptual hashing scheme, where the two branches focus on image visual features and text features, respectively. Existing perceptual hashing schemes cannot solve the problem of the tiny proportion of text tampering detection, while simple text detection is unable to solve the problem of background region-aware matching. To address these issues, we extract text information via optical character recognition (OCR) and then generate the text features using the bidirectional encoder representations from Transformers (BERT). Visual features of the image are extracted from the local and global features of the image using ResNet and Vision Transformer cascades, and then fused to generate the final hash sequence through the fully connected layer. The proposed network considers both image visual features and textual information to verify that the document image has not been tampered with. In our network, the OCR module enables accurate and intelligent text detection and recognition, particularly for dealing with text tampering that has only been conducted in tiny portions. It also provides more efficient and robust text recognition services. Experimental results show that the proposed hashing scheme is robust and discriminative in document images.

To address the issues of privacy leakage and copyright infringement in screen-camera scenarios, we propose a robust image watermarking method, which incorporates kolmogorov–arnold network (KAN) blocks and a simulation-enhanced noise pool to resist screen-camera noise attacks. Specifically, we first modify the traditional convolutional blocks for processing high-dimensional features in the U-Net-based encoder to KAN blocks. This operation enhances the ability of encoder to model nonlinear relationships between complex features, while preserving global structure of the original image and minimizing the damage to local details caused by watermark embedding, thereby improving visual quality of the watermarked image. Additionally, to enhance the robustness of the proposed method against complex screen-camera noise attacks, a simulation-enhanced noise pool containing mathematical models and a deep noise simulation network, called NSim-Net, is designed. Especially, in NSim-Net, adversarial training between the simulator based on the improved U-Net and the discriminator based on PatchGAN effectively improves the ability to simulate complex noise. Experimental results demonstrate that, compared to typical screen-camera resilient watermarking methods, the watermarked image generated by the proposed method achieves a maximum peak signal-to-noise ratio (PSNR) improvement of 4.78 dB. Furthermore, based on our simulation-enhanced noise pool, the watermark extraction accuracy of the proposed method exceeds 98% under various screen-camera noise attacks.

In recent years, due to the rich parameters contained in deep neural network (DNN) models, researchers have proposed DNN model steganography, using DNN models as carriers. In this paper, we propose a constructive DNN model steganography method based on parameter initialization. Unlike existing DNN model steganography methods that embed secret information into a pre-trained DNN model, we generate parameters containing secret information through parameter initialization for a DNN model structure, and the embedded secret information can still be extracted after model training. Specifically, we first generate the model parameters needed for the DNN model structure through a secret information-driven encoder, and then we jointly train the encoder and decoder to ensure the correct extraction of secret information. Additionally, we introduce a noise layer to simulate the model training process to guarantee the robustness of our method. Experimental results demonstrate that our method not only achieves high hiding capacity but also exhibits satisfactory stealthiness and robustness. Furthermore, our method is generalizable, which can be applied to various network structures, such as multilayer perceptron (MLP), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Transformers.

In recent years, neural network models have been widely used in many tasks, however, tampering operations from malicious attackers, e.g., backdoor attacks and parameter malicious tampering, can easily degrade the model performance or cause a malfunction. To protect the integrity of neural network model, in this paper, we propose a neural network watermarking scheme with hierarchical recoverability (NNWHR), which not only can identify and locate the tampered parameters, but also can recover the tampered parameters in a hierarchical way. Detailedly, the parameters of to-be-protected network layers are first sorted according to the parameter importances, which are calculated through a specifically designed strategy for parameter evaluation. Then, the reference sharing mechanism is used to generate more number of recovery bits and provide greater perfect recovery probabilities for the parameters with higher importances, which can also deal with larger tampering rates through bit interleaving. Finally, the recovery bits and the authentication bits of model parameters are incorporated as watermark bits and embedded into the model redundant space after scrambling. Experimental results show that our scheme can locate tampered model parameters and recover corresponding model performance with satisfactory accuracy, and can also be applied to eliminate backdoor attacks. In addition, our scheme exhibits satisfactory generalizability, which makes it applicable to various types of neural networks.

Generative steganography (GS) is a novel data-hiding technique that generates stego images directly from secret data without using cover images, which is different from traditional steganography. However, existing steganography methods have shortcomings in terms of hiding capacity, extraction accuracy, and diversity of stego images. To address these limitations, we propose a high-performance Conditional Flow-based Generative Steganography (CFGS). First, to achieve exact extraction of secret data in high-capacity scenarios, we hide secret data in the frequency domain to resist the impact of stego image distortion. In addition, to enhance the diversity of stego images, we introduce a novel conditional generative flow model (C-Flow) to generate stego images, which consists of two newly designed layers, the Conditional Attention-based Affine Coupling layer and the Conditional Invertible Norm layer. C-Flow can accurately guide the visual content of stego images through different conditions, enhancing the diversity of stego images. Our approach is the first GS method capable of conditional guidance of stego image visual content, and achieves extraction accuracy of hidden secret data equal to or close to 100% for payloads up to 1 bit-per-pixel (bpp). Extensive experiments demonstrate that our proposed approach outperforms state-of-the-art GS methods.

Due to the powerful feature extraction capabilities of deep neural networks (DNNs), deep image hashing has extensive applications in the fields such as image authentication, copy detection and content retrieval, making its security a critical concern. Among various security metrics, collision resistance serves as a crucial indicator of deep image hashing methods. Research on collision attacks not only reveals the potential vulnerabilities of deep image hashing but also can promote the development of more robust and secure hashing methods. In this paper, we propose a novel generative collision attack scheme, which achieves several advantages over existing attack schemes based on adversarial examples. Our scheme requires no additional perturbations added to the image, and can simultaneously generate multiple hash collision images of different classes specified by the attacker. To the best of our knowledge, this is the first generative collision attack scheme effective across various deep image hashing methods. Specifically, our attack framework consists of three parts, i.e., a Hash-to-Noise Network (HTNN), a pretrained BigGAN generator and a conditional discriminator. The designed HTNN embeds the hash code of the target image and the attacker-specified generation class information into a “noise” vector. By optimizing various hash distance loss functions between the generated and target images, this “noise” guides the generator to directly generate images that meet the collision requirement. At the same time, the discriminator ensures that the generated images are visually realistic. Extensive experimental results verify that our scheme can effectively generate multiple high-quality images with attacker-specified classes, achieving the high success rate of hash collision attack and the applicability across state-of-the-art deep hashing methods.

Although screen-camera resilient watermarking addresses issues such as privacy leakage and copyright infringement in digital images to some extent during screen-camera communication. However, in screen-camera scenarios, uncontrolled shooting environments, various display devices, and different lens types introduce more complex noise into the watermarked images. Because some noise generated during the screen-camera process cannot be quantitatively analyzed, the integrity of the embedded watermark is compromised, making copyright verification and information acquisition still difficult. To solve this problem, we establish a large-scale screen-camera image dataset (SCISet) and propose a noise simulation network (NoS-Net). Specifically, we obtain 36,000 screen-camera images under various shooting environments with multiple types of screens and cameras. Then, we use SCISet to train the proposed NoS-Net based on the U-Net architecture, which can learn multi-level and complementary feature information of screen-camera images, enhancing its ability to simulate complex noise. Experimental results show that integrating the proposed NoS-Net into mainstream screen-camera resilient watermarking methods significantly improves their ability to resist screen-camera noise attacks. Furthermore, the diversity of SCISet plays an important role in advancing robust watermarking research.

Cloud services have attracted extensive attention due to low cost, agility and mobility. However, when processing data on cloud servers, users may worry about semi-honest third parties stealing private information from them, hence, data encryption is applied for privacy protection. Inpainting is a technique that reconstructs certain undesirable regions in an image through an imperceptible manner, which can be accomplished by searching for well-matching candidate patches and copying them to to-be-inpainted locations. However, when the image is encrypted, the matched candidate patch searching is a challenging dilemma. Therefore, tackling these data-privacy issues for image inpainting over a cloud infrastructure, we propose an image inpainting scheme using Markov random field (MRF) modeling in encrypted domain. In this scheme, the sender encrypts the to-be-inapinted image by using a homomorphic cryptosystem that supports homomorphic ciphertext comparison. Then, the cloud realizes the MRF-based inpainting for encrypted images through some specific homomorphic operations. In addition, secure context descriptors are utilized to improve the inpainting of textures and structures. Finally, the receiver obtains the inpainted result through image decryption. The proposed scheme is proved to be secure through various cryptographic attacks. Qualitative and quantitative results demonstrate our scheme achieves better inpainted results in structure compared with state-of-the-art schemes in encrypted domain.

Multi-image steganography refers to the technique of embedding multiple secret images into a single cover image while ensuring that the secret images remain imperceptible and can be perfectly recovered by the recipient. Traditional single-image-based steganography often leads to noticeable contour shadows or color distortions in the cover image, making the hidden image more detectable. In contrast, cascaded invertible neural network-based steganography introduces a large number of parameters, complicating the network structure and resulting in a time-consuming learning and training process. To address the above problems, this paper proposes a novel flow-based, end-to-end multi-image invertible steganography framework (StegFlow), which effectively integrates forward and backward data flows for image hiding and recovery. The framework employs cascading operations to enable deep hiding of multiple secret images. To enhance the coupling capabilities, we introduce an invertible permutation layer that disrupts the channel arrangement order, allowing the coupling layer to more accurately guide the embedding of secret information into regions of the image that are easy to hide and recover. In addition, a high-frequency distribution mapping (HFDM) is designed to model the lost high-frequency information during image hiding process, significantly improving the recovery performance of the secret images. Extensive experiments are performed over multiple classical datasets, and the results demonstrate that compared to state-of-the-art (SOTA) models, the proposed framework can achieve a superior overall performance in terms of visual quality and anti-steganalysis capability. Specifically, our scheme can improve the hiding accuracy (measured by PSNR) by over 3 dB and the recovery accuracy by over 1 dB when hiding two secret images.

JPEG reversible data hiding (RDH) refers to covert communication technology to accurately extract secret data while also perfectly recovering the original JPEG image. With the development of cloud services, a large number of private JPEG images can be efficiently managed in cloud platforms by embedding user ID or authentication labels. Nevertheless, data embedding operations may inadvertently disrupt the encoding sequence of the original JPEG image, resulting in severe distortion of the host image when it is re-compressed to JPEG format. To address this problem, this paper proposes a new JPEG RDH scheme based on block sorting optimization and dynamic iterative histogram modification. We firstly design a block ordering optimization strategy by combining the number of zero coefficients and the quantization table values of non-zero coefficients in a DCT block. Subsequently, a dynamic iterative histogram modification scheme is proposed by considering the local features and embedding capability of histograms generated from different texture images. According to the given payloads, we introduce different parameters to control the iterations of two-dimensional histogram and then adaptively generate the optimal histogram modification mapping, which can realize low JPEG file size increments by guaranteeing most of the AC coefficients unchanged as much as possible. Numerous experiments have shown that our scheme can achieve an effective balance among embedding capacity, visual quality, file size increment, computational complexity, and outperforms the state-of-the-arts in terms of the above metrics.

Designing an end-to-end encryption method for images using the non-linear properties of deep neural networks (DNNs) has gradually attracted the attention of researchers. In this article, we introduce a new framework for DNN-based image encryption that embeds a plaintext image as a secret message into a random noise to obtain a ciphertext image. Based on this, we propose an end-to-end robust image encryption method based on the invertible neural network (INN), which can realize secure encryption and resistance to common image processing attacks. Specifically, the INN is exploited as the shared-parameter encoder and decoder to achieve end-to-end encryption and decryption. The ciphertext image can be obtained through the forward process of the INN by inputting the plaintext image and the key, while the decrypted image can be obtained through the backward process of the INN by inputting the ciphertext image and the key. To enhance the security of our method, we design an information reinforcement module to guarantee the encryption effect and the sensitivity of the key. In addition, to improve the robustness of our method, an attack layer is employed for noise simulation training. Experimental results show that our method not only can realize secure encryption but also can achieve the robustness such as resisting JPEG compression, Gaussian noise, scaling, mean filtering, and Gaussian blurring effectively.

With accelerating development of artificial intelligence, neural network models have been applied in many fields. The structure designing and training for models consume vast manpower and computing resources, which are the core interests of related research institutions and enterprises. However, the high-value attributes of neural network models also attract the attention of pirates, who may steal them for illegal profits and also slightly modify model parameters to escape model piracy detection. In order to solve the problem, in this work, we propose a robust and secure model hashing method based on dynamic branch reorganization and multi-feature fusion. Detailedly, we dynamically adjust the branches in our model hashing network to extract the robust features of all kinds of model parameters for generating the hash sequence. Besides, we integrate the encryption and the feature matrix generation to a unified stage in the hash generation for resisting possible encryption escape attack. Thus, the pirated models, even with some modifications, can be correctly detected through calculating hash distances. Experimental results demonstrate the effectiveness and superiority of our model hashing method with respect to pirated model detection, non-pirated model discrimination and security.

Perceptual hashing is a cutting-edge technique in the field of digital multimedia security, which maps the perceptual content of multimedia information to a fixed-length hash sequence to achieve content authentication. This survey provides a systematic overview of the definition, basic steps, main characters, and application scenarios of perceptual hashing. According to the different authentication objects, representative schemes of perceptual image hashing, perceptual video hashing, and perceptual hashing for neural network models are introduced, respectively. Both perceptual image hashing and perceptual video hashing can be divided into classical methods-based schemes and learning-based schemes, where learning-based schemes can be subdivided into supervised and unsupervised. Classical methods-based image hashing schemes can be divided into four categories: local feature-based, transformation-based, statistical feature-based, and dimensionality reduction-based. Classical methods-based video hashing schemes are mainly categorized into spatial feature-based schemes and spatial-temporal feature-based schemes. Additionally, we introduce the dataset composition and hash distance metric strategies for perceptual hashing and analyze the performance of some representative schemes. Finally, we summarize the existing schemes and offer prospects for future research directions and development trends.

Object detection on remote sensing images (RSIs) is a critical component of remote sensing image processing techniques. Nonetheless, as the complexity of the model structure increases, more training data is required to prevent a severe decline in object detection performance. This requirement highlights the potential of few-shot object detection techniques. At present, few researches have been investigated for few-shot object detection on RSIs. To address this situation, we propose the saliency-guided multi-head distribution calibration network (SMDC-Net) by building upon the existing fine-tuning-based two-stage few-shot object detection approach. We employ an RSIs salient object detection (SOD) branch that leverages the feature of RSIs to predict the saliency maps. These predicted saliency maps are used as an attention map to augment the feature of RSIs. Meanwhile, to guarantee the ability of the network to identify objects within both the base and novel categories accurately, we design a multi-head detector which can recognize objects within base and novel categories separately while introducing a consistency loss to supervise the consistency of the multi-head predicted labels. We evaluate the performance of two widely recognized RSIs datasets (i.e., DIOR and NWPU VHR-10) within various experimental settings for comparison and ablation analysis. The results illustrate that SMDC-Net enhances the detection performance of novel categories approximately 3% compared to the state-of-the-art MM-RCNN, while preserving the performance of base categories.

How to protect the intellectual property (IP) of neural network models has become a hot topic in current research. Model hashing as an important model protection scheme, which achieves model IP protection by extracting model feature-based, compact hash codes and calculating the hash distance between original and suspicious models. To realize model IP protection across platforms and environments, we propose a robust hashing scheme for neural network models via heterogeneous graph representation, which can effectively detect the illegal copy of neural network models and doesn't degrade the model performance. Specifically, we first convert the neural network model into a heterogeneous graph and analyze its node attribute data. Then, a graph embedding learning method is used to extract the feature vectors of the model based on different attribute data of graph nodes. Finally, the hash code that can be used for model copy detection is generated based on the designed hash networks with quantization and triplet losses. Experimental results show that our scheme not only exhibits satisfactory robustness to different types of robustness graph attacks but also achieves satisfactory performances of discrimination and generalizability.

In order to achieve the secure, efficient storage and transmission of medical images, we propose a joint lossless compression and encryption (JLCE) scheme. First, according to the intra-block correlation degree, the original medical image is divided into two non-overlapping regions with strong correlation and weak correlation. Then, a linear prediction method is performed on the strong correlation region to generate prediction errors; while the integer discrete Tchebichef transform (iDTT) with the properties of energy compaction and perfect image reconstruction is exploited to compact the energy of the weak correlation region and produce the transformed coefficients. Finally, a secure arithmetic encoding algorithm is presented to encode the prediction errors and transformed coefficients and output the encrypted and compressed bitstream. Without secret keys, the outputted encoded result can be decoded by our scheme, but the decoded result doesn’t disclose the content of the original medical image. Experimental results show that, the proposed scheme has satisfactory format compatibility and security and also achieves better performances of compression ratio and computational efficiency compared with some state-of-the-art schemes.

With the development of social network, a large number of private JPEG images are stored in social cloud platform. Correspondingly, the platform embeds user ID or authentication labels to manage these privacy images, preventing them from being arbitrarily accessed or tampered by illegal persons. However, data embedding in JPEG domain inevitably produces irreversible modifications to DCT coefficients, thus resulting in obvious or even serious distortion in the host JPEG images. To address this problem, this paper proposes an efficient JPEG reversible data hiding (RDH) method by constructing progressive two-dimensional histogram mappings. We firstly design distortion function to calculate the cost of each DCT frequency band, and then sort them to build histogram mapping containing a series of coefficient pairs. Subsequently, a progressive mapping mechanism is introduced to maintain most of AC coefficients unchanged. According to the given capacity, this mechanism can adaptively generate an optimum two-dimensional histogram mapping to embed secret messages. Our scheme can achieve an effective balance among embedding capacity, visual quality of the marked image and file size expansion, while keeping high cost-performance complexity. Extensive experiments demonstrate that our method outperforms existing JPEG RDH schemes in terms of visual quality and file size increment of the marked image, and provides an efficient solution for the confidentiality and security access problem of sensitive private image in cloud environment.

A robust reversible watermarking (RRW) algorithm enables the extraction of the watermark and the restoration of the cover image without attacks while ensuring the watermark’s extraction when the image is under attack. Existing RRW methods mainly focused on achieving robustness against geometric attacks such as rotation and scaling by embedding watermarks within the global inscribed circle of an image. However, the geometric transformations targeted by the existing methods cannot cope with combined attacks that include cropping, which is a real application scenario for geometric attacks. To extend the robustness of the watermarking algorithm, this paper proposes a local Zernike moments (ZMs) embedding strategy based on feature point extraction and selection. For each local circular domain, the same watermark is embedded in the magnitude of the ZMs. After embedding, all the compensation information used to recover the robust embedded regions is embedded outside these local circular domains in a reversible way. When attacks occur, especially combined attacks involving cropping, by using side information, the local watermarked regions in the image can be localized to extract the robust watermark. Experimental results show the superiority of the proposed method under various combined attacks that include cropping operations.

This paper tackles a recent challenge in designing an efficient steganographic distortion model, whose goal is to accurately measure the modification cost of a pixel and help design steganographic schemes with high undetectability. Existing distortion models mostly assume that different modification directions of a pixel have an identical cost value and that pixel modifications are independent. These assumptions, however, may not lead to good steganography design because the modification direction of neighbouring pixels may affect the cost measurement of the current pixel. To address this problem, we propose a new distortion calculation method using dynamic cost correction and multi-modality distortion ensemble. The proposed scheme first employs a given distortion model to generate the original cost map. The cost of each pixel is then dynamically adjusted with majority voting according to the modification directions of its neighbouring pixels. Furthermore, different distortion calculation models are integrated to make the final decision on the distortion of each pixel. Experimental results show that compared to existing additive distortion-based steganographic schemes and deep learning-based steganographic schemes, steganography using our proposed distortion model performs better when tested against state-of-the-art steganalysis methods.

This paper introduces a novel, lightweight deep invertible steganography network (LiDiNet) for image-in-image steganography. Traditional methods, while hiding a secret image within a cover image, often suffer from contour shadows or color distortion, making the secret image easily detectable. Additionally, the superposition of multiple invertible networks may complicate network structures and introduce excessive parameters, making the network training and learning processes difficult. LiDiNet addresses these issues by employing multiple invertible neural networks (INNs) to create a pair of coupled invertible processes for image hiding and recovery. A key innovation is the invertible convolutional layer, which streamlines the affine coupling structure in each INN for improved information fusion. In addition, a series of adaptive coordination spatial-wise attention modules are integrated to enhance the network’s effectiveness in image hiding and recovery, thereby elevating the security of the steganography. LiDiNet’s lightweight structure ensures both high-capacity steganography and robustness against steganalysis. Extensive experiments across various image datasets demonstrate LiDiNet’s superior performance, particularly in visual quality and anti-steganalysis capability, compared to existing methods.

Face information in public images is vulnerable to tampering. Some studies have used pre-embedded watermarks to detect tampering but cannot recover the original face. To address this, we propose a proactive face hiding network that conceals face information in the background region for the first time. Our framework includes three U-Net-based modules: a preparation network, an encoder, and a recovery network. Special loss functions are designed to achieve our objective of recovering the original face from a protected image attacked by face swapping. In addition, we develop a neural network-based JPEG simulator and a differentiable simulator, offering a fresh perspective on addressing the robustness problem associated with JPEG compression. Our method generates protected images with a peak signal-to-noise ratio (PSNR) of 40.947 dB in experiments. Even after different face attacks, the recovered images maintain PSNR between 28.368 and 33.847 dB. After the attack of JPEG compression, the PSNR of the recovered image decreases by a maximum of 2.142 dB. Our scheme effectively generates high-quality protected images that resist face swapping and JPEG compression attacks, enabling recovery of the original faces.

Multi-view clustering usually attempts to improve the final performance by integrating graph structure information from different views and methods based on anchor are presented to reduce the computation cost for datasets with large scales. Despite significant progress, these methods pay few attentions to ensuring that the cluster structure correspondence between anchor graph and partition is built on multi-view datasets. Besides, they ignore to discover the anchor graph depicting the shared cluster assignment across views under the orthogonal constraint on actual bases in factorization. In this paper, we propose a novel Dual consensus Anchor Learning for Fast multi-view clustering (DALF) method, where the cluster structure correspondence between anchor graph and partition is guaranteed on multi-view datasets with large scales. It jointly learns anchors, constructs anchor graph and performs partition under a unified framework with the rank constraint imposed on the built Laplacian graph and the orthogonal constraint on the centroid representation. DALF simultaneously focuses on the cluster structure in the anchor graph and partition. The final cluster structure is simultaneously shown in the anchor graph and partition. We introduce the orthogonal constraint on the centroid representation in anchor graph factorization and the cluster assignment is directly constructed, where the cluster structure is shown in the partition. We present an iterative algorithm for solving the formulated problem. Extensive experiments demonstrate the effectiveness and efficiency of DALF on different multi-view datasets compared with other methods.

Reversible data hiding (RDH) has been extensively studied in the field of multimedia security. Embedding capacity is an important metric for RDH performance evaluation. However, the embedding capacity of existing methods for independent and identically distributed (i.i.d.) gray-scale signals is still not good enough. In this paper, we propose a high-capacity RDH code construction method that employs asymmetric numeral systems (ANS) coding as the underlying coding framework. Based on the proposed framework, two RDH methods are presented. First, we propose a static RDH method that takes the constant host probability mass function (PMF) as input parameters and offers high embedding performance. Then, we give a dynamic RDH method that can eliminate the need for transmitting the host PMF in advance by designing a reversible dynamic probability calculator. The simulation results on discrete normally distributed signals demonstrate that the performance of the proposed static method is very close to the expected rate-distortion bound, and the proposed dynamic method can achieve satisfactory embedding capacity without prior knowledge of host PMF at the cost of slightly sacrificing steganographic data quality. Moreover, the experimental results on gray-scale images show that the proposed static method provides higher peak signal-to-noise ratio (PSNR) values and larger embedding capacities than some state-of-the-art methods, e.g., the embedding capacity of image Lena is as high as 3.571 bits per pixel.

Multi-image steganography refers to a stegano- graphic method where a user tries to hide multiple confidential images within a single cover image, and all confidential images can be correspondingly recovered perfectly by the recipient. Multi-image steganography essentially belongs to a high-capacity image steganographic scheme, but such high hiding capacity may easily cause severe contour shadows or color distortion of steganographic images, resulting in a significant reduction in anti-steganalysis capability. To address the above problem, this article designs a deep invertible neural network by introducing spatial-channel joint attention mechanism, in which the confidential image hiding and recovery can be regarded as a pair of coupled invertible processes. Specifically, a series of simple invertible networks having the same structure are firstly used to construct a cascaded deep invertible neural network framework, in which multiple confidential images can be sequentially embedded into a single cover image through a series of flexible cascaded iterative operations. Subsequently, spatial-channel joint attention module is designed to re-construct invertible network model, which can guide the embedding of secret information into more secure image regions. Accordingly, this joint attention mechanism can effectively address the problem of visual quality and security degradation of steganographic images due to high embedding capacity. Extensive experiments demonstrate that our scheme can obtain superior performance over different large-scale image sets, and outperforms state-of-the art methods with higher visual quality and stronger anti-steganalysis capability.

Due to the limited number of stable image feature descriptors and the simplistic concatenation approach to hash generation, existing hashing methods have not achieved a satisfactory balance between robustness and discrimination. To this end, a novel perceptual hashing method is proposed in this paper using feature fusion of fractional-order continuous orthogonal moments (FrCOMs). Specifically, two robust image descriptors, i.e., fractional-order Chebyshev Fourier moments (FrCHFMs) and fractional-order radial harmonic Fourier moments (FrRHFMs), are used to extract global structural features of a color image. Then, the canonical correlation analysis (CCA) strategy is employed to fuse these features during the final hash generation process. Compared to direct concatenation, CCA excels in eliminating redundancies between feature vectors, resulting in a shorter hash sequence and higher authentication performance. A series of experiments demonstrate that the proposed method achieves satisfactory robustness, discrimination and security. Particularly, the proposed method exhibits better tampering detection ability and robustness against combined content-preserving manipulations in practical applications.

In this article, an effective print-camera (P-C) resistant image watermarking scheme is proposed. To achieve watermark robustness, most of existing works try to simulate P-C noise by a sophisticated math model. However, the diversity of P-C noises in the real world is ignored, and the watermarked image may not attain a good balance between high robustness and low distortion. To address the problem, we construct an efficient end-to-end network architecture for watermark embedding and extraction. To be specific, a deep noise simulation network (NSN) is designed to simulate the fusion process of real P-C noises, which can help to generate high-robust watermarked image. Also, a multitask loss function based on just-noticeable-difference (JND) is proposed to conduct constrained learning for residual image containing watermark information, thus, the distortion of generated watermarked image can be significantly reduced. Experimental results show that our scheme can achieve high robustness against P-C process while maintaining a satisfactory watermark capacity and visual quality of watermarked image.

JPEG image manipulation localization aims to accurately classify and locate tampered regions in JPEG images. Existing image manipulation localization schemes usually consider diverse data streams of spatial domain, e.g. noise inconsistency and local content inconsistency. They, however, easily ignore an objective scenario: data stream features of spatial domain are hard to directly apply to compressed image format, e.g., JPEG, because tampered JPEG images may contain severe re-compression inconsistency and re-compression artifacts, when they are re-compressed to JPEG format. As a result, the traditional localization schemes relying on general data streams of spatial domain may result in a large number of false detection of tampered region in JPEG images. To address the above problem, we a new JPEG image manipulation localization scheme, in which a wide-receptive-field attention network is designed to effectively learn JPEG compressed artifacts. We firstly introduce the wide-receptive-field attention mechanism to re-construct U-Net network, which can effectively capture contextual information of JPEG images and analyze tampering traces from different image regions. Furthermore, a flexible JPEG compressed artifact learning module is designed to capture the image noise caused by JPEG compression, in which the weights can be adjusted flexibly based on image quality, without the need for decompression operations on JPEG images. Our proposed method can significantly strength the differentiation capability of detection model for tampered and non-tampered regions. A series of experiments are performed over different image sets, and the results demonstrate that the proposed scheme can achieve an overall localization performance for multi-scale JPEG manipulation regions and outperform most of state-of-the-art schemes in terms of detection accuracy, generalization and robustness.

In recent decades, many perceptual image hashing schemes for content authentication have been proposed. However, existing algorithms cannot provide satisfactory robustness and discrimination in the face of complex manipulations in real scenarios. In this work, we propose a novel perceptual robust image hashing scheme with transformer-based multi-layer constraints. Specifically, we first exploit the Transformer structure into the field of perceptual image hashing, and an integrated loss function is designed to optimize the training of the model. In addition, to solve the issue of the simple content-preserving manipulations used in previous datasets, we construct a more challenging image dataset based on various manipulations, which can deal with complex image authentication scenarios. Experimental results demonstrate that our scheme achieves competitive results compared with existing schemes.

In this paper, we propose an end-to-end perceptual robust hashing scheme for video copy detection based on unsupervised learning. Firstly, the spatio-temporal information in videos is effectively fused and condensed into high-dimensional features through a 3D self-attention, multi-scale feature fusion model based on 3D-CNN, in which the Inception block and the 3D self-attention mechanism are integrated. Then, we calculate the correlation distances between the extracted features to differentiate perceptual contents. Based on the similarity relationship, we can dynamically generate the pseudo-labels and exploit them to further guide the model training for video hash generation. In addition, we design the dual constraints to make the hash code obtain satisfactory robustness and discrimination. Extensive experiments demonstrate that the proposed scheme achieves superior performance of copy detection compared with existing schemes and performs well even in the case of untrained manipulations.

Since the significant advancements and open-source support of latent diffusion models (LDMs) in the field of image generation, numerous researchers and enterprises start fine-tuning the pre-trained models to generate specialized images for different objectives. However, the criminals may turn their attention to generate images by LDMs and then carry out illegal activities. The watermarking technique is a typical solution to deal with this problem. But, the post-hoc watermarking methods can be easily escaped to obtain the non-watermarked images, and the existing watermarking methods designed for LDMs can only embed a fixed message, i.e., the to-be-embedded message cannot be changed unless retraining the model. Therefore, in this work, we propose an end-to-end watermarking method based on the encoder-decoder (ENDE) and message-matrix. The message can be embedded into generated images through fusing the message-matrix and intermediate outputs in the forward propagation of image generation based on LDM. Thus, the message can be flexibly changed by utilizing the message-encoder to generate message-matrix, without training the LDM again. On the other hand, the security mechanism in our watermarking method can defeat the attack that the users may escape the message-matrix usage during image generation. A series of experiments demonstrate the effectiveness and the superiority of our watermarking method compared with SOTA methods.

In recent years, many perceptual authentication hashing schemes have been proposed, especially for image content authentication. However, most of the schemes directly use the dataset of image processing during model training and evaluation, which is actually unreasonable due to the task difference. In this paper, we first propose a specialized dataset for perceptual authentication hashing of images (PAHI), and the image content-preserving manipulations used in this dataset are richer and more in line with realistic scenarios. Then, in order to achieve satisfactory perceptual robustness and discrimination capability of PAHI, we exploit the continuous neural architecture search (NAS) on the channel number and stack depth of the ConvNeXt architecture, and obtain two PAHI architectures i.e., NASRes and NASCoNt. The former has better overall performance, while the latter is better for some special manipulations such as image cropping and background overlap. Experimental results demonstrate that our architectures both can achieve competitive results compared with SOTA schemes, and the AUC areas are increased by 1.6 (NASCoNt) and 1.7 (NASRes), respectively.

Few-shot semantic segmentation is a technique that is receiving increasing attention. The aim of this approach is to enable models to segment objects with a few support images (usually 1, 5, 10, etc.). At present, few-shot semantic segmentation has made great progress in the field of Natural Scene Image (NSI), but these methods cannot be applied directly to the field of Remote Sensing Image (RSI). In order to overcome this challenge, we propose a novel semantic segmentation network structure that integrates prototype information with global edge information to achieve more accurate prototype matching results. In addition, we design a comprehensive weighted loss function to monitor the training process to help overcome the challenges. Results of the performance comparison with state-of-the-art few-shot semantic segmentation methods demonstrate the superiority of the proposed method.

Reversible data hiding (RDH) has been investigated for over two decades. Depending on the application scenario, it can be divided into RDH and reversible data hiding in encrypted images (RDHEI). Interestingly, almost all studies on RDH/RDHEI have been conducted on gray-scale images, and relatively few studies have been conducted on color images compared to those on gray-scale images. Moreover, very few studies have been undertaken on palette images as a widely used image format. For palette images in which pixels are not gray-scale levels but color table indexes, it is difficult to apply traditional RDH/RDHEI methods directly. Therefore, we propose a new framework for RDH/RDHEI specifically for palette images. This framework adds a route selection algorithm before the conventional RDH/RDHEI approach. To be specific, we propose a method named the shortest route with correlation and frequency selection to reorder the color table, followed by a correlation reconstruction of the remapped index image according to this color table. The experimental results show the improvement brought by our proposed route selection to the existing RDH/RDHEI methods in palette images.

Reversible data hiding in encrypted images (RDHEI) is an essential data security technique. Most RDHEI methods cannot perform well in embedding capacity and security. To address this issue, we propose a new RDHEI method using Chinese remainder theorem-based secret sharing (CRTSS) and hybrid coding. Specifically, a hybrid coding is first proposed for RDH to achieve high embedding capacity. At the content owner side, a novel iterative encryption is designed to conduct block based encryption for perfectly preserving the spatial correlation of original blocks in their encrypted blocks. Then, the CRTSS with the constraints is exploited to generate multiple encrypted image shares, in which spatial correlations of the encrypted blocks are also preserved. Meanwhile, the CRTSS provides good security properties for the proposed method. Since there are strong spatial correlations in the blocks of each share, the data-hider can exploit the proposed hybrid coding to perform data embedding for improving capacity. On the receiver side, even if some shares are corrupted/missing, the original image can be losslessly recovered as long as enough uncorrupted marked shares are obtained. Experiment results show that the proposed RDHEI method outperforms some state-of-the-art methods, including some secret sharing (SS) based methods in terms of embedding capacity.

Data in real world are usually characterized in multiple views, including different types of features or different modalities. Multi-view learning has been popular in the past decades and achieved significant improvements. In this paper, we investigate three challenging problems in the field of incomplete multi-view representation learning, namely, i) how to reduce the influences produced by missing views in multi-view dataset, ii) how to learn a consistent and informative representation among different views and iii) how to alleviate the impacts of the inherent noise in multi-view data caused by high-dimensional features or varied quality for different data points. To address these challenges, we integrate these three tasks into a problem and propose a novel framework termed Noise-aware Incomplete Multi-view Learning Networks (NIM-Nets). NIM-Nets fully utilize incomplete data from different views to produce a multi-view shared representation which is consistent, informative and robust to noise. We model the inherent noise in data by defining the distribution $\Gamma $ and assuming that each observation in the incomplete dataset is sampled from the distribution $\Gamma $ . To the best of our knowledge, this is the first work to unify learning the consistent and informative representation, alleviating the impacts of noise in data and handling the view-missing patterns in multi-view learning into a framework. We also first give a definition of robustness and completeness for incomplete multi-view representation learning. Based on NIM-Nets, we present joint optimization models for classification and clustering, respectively. Extensive experiments on different datasets demonstrate the effectiveness of our method over the existing work based on classification and clustering tasks in terms of different metrics.

Image manipulation localization is a technique that can efficiently segment the tampered regions from a suspicious image. Existing work usually trains a detection model by fusing the features from diverse data streams, e.g., noise inconsistency, recompression inconsistency, and local inconsistency. They, however, ignore a fact that not all tampered images contain these data streams. As a result, high feature redundancy may cause a large number of false detection for tampered region. To address this problem, this paper designs an end-to-end high-confidence localization network architecture. First, deep convolutional neural networks are utilized to extract multi-scale feature sets from the RGB streams. We then design a semantic refined bi-directional feature integration module to fully fuse multi-scale adjacent features and significantly enhance feature representation. Subsequently, morphological operations are introduced to extract multi-scale edge information, which can efficiently reduce feature redundancy by generating wider high-resolution edges during image reconstructing. Finally, a deep semantic residual decoder is sequentially re-constructed by spreading deep semantic information into each decoding stage. The proposed method can not only improve the manipulation localization accuracy, but also guarantee the model robustness. Extensive experiments demonstrate that our method can obtain an effective performance in locating forged regions over different large-scale image sets, and outperforms most of state-of-the-art methods with higher localization accuracy and stronger robustness.

JPEG image encryption aims at effectively converting the original JPEG image into a noise-like image that does not contain any useful information of original image. Existing schemes for JPEG image encryption, however, may not attain a good balance in terms of file size increment and encryption security. To address the problem, we design a novel JPEG image encryption scheme. Different from existing schemes, we first predict DC coefficients by an adaptive prediction method. Subsequently, the histogram of DC coefficient prediction errors is encrypted by combining the prediction errors and random integers to reduce the encoded length, which can ensure a very small increment of file size. Furthermore, we construct the RS (run/size) pairs in each DCT block and then implement the permutation for both RS pairs extracted from the upper left corner of each DCT block and all DCT blocks excluding DC coefficients, which can further distort the image contents. Extensive experiments demonstrate that, compared with existing JPEG image encryption schemes, our scheme can ensure not only the JPEG format compatibility for encrypted image, but also keep a very small file size increment and the superior security performance.

With the rapid development of neural network, a vast number of neural network models have been developed in recent years, which condense numerous manpower and hardware resource. However, the original models are at risk of being pirated by the adversary to obtain illegal profits. On the other hand, malicious tampering on models, such as implanting the vulnerability and backdoor, may cause catastrophic consequences. We propose a model hash generator method to protect neural network models. Detailedly, our model hash sequence is composed of two parts: one is the model piracy identification hash, which is based on the dynamic convolution and a dual-branch network; the other is the model tampering localization hash, which can help the model owner to accurately detect the tampered locations for further recovery. Experimental results demonstrate the effectiveness of the proposed method for neural network model protection.

A lot of excellent neural network models are valuable wealth to the field of artificial intelligence, which may be plagiarized and distributed without authorization. For this reason, few research establishments and industries reveal the internals of their neural network models. To authenticate suspicious pirated models, this letter proposes a gray-box hashing method for the neural network models that designed for image classification. In the proposed method, the hash sequence of original model can be extracted without knowing both the structure and weight parameters except the vectors in output layer. To the best of our knowledge, this is the first work focusing on gray-box perceptual model hashing to identify and authenticate neural network models. Experimental results show that our method performs satisfactory perceptual robustness and discrimination capability, and can effectively classify perceptual similar versions of the original model and distinct models.

The training process of a neural network model requires plenty of costs, and so the intellectual property of neural network models should be protected. To this end, we propose a robust watermarking scheme for neural network models in this paper. In our scheme, an independent network is specially designed to help embedding watermarks into a given host network, and also be used for watermark extraction. The independent network is designed based on the residual structure which is sensitive to the parameter changes of the host network and conducive to finding suitable embedding locations. In addition, some residual blocks are randomly discarded during watermark embedding, which can increase the robustness against popular model attacks. Experimental results show that our scheme achieves satisfactory watermark verification performance without decreasing the original performance of the host network, even if the host network has been maliciously tampered.

In this paper, we propose an enhancing steganographic scheme by random generation and ensemble stego selection. Different from existing steganography that only focuses on distortion function designing, our scheme considers both distortion model and optimized stego generation. In specific, for given cover, we firstly train an universal steganalyzer to calculate its gradient map, which is referenced to randomly adjust cost distribution of this cover. Multiple candidate stegos are sequentially generated by combining adjusted cost and syndrome trellis coding. Furthermore, we build an ensemble selection mechanism to effectively determine the candidate that is closest to the statistical characteristics of cover image as the final steganographic image. Comprehensive experiments demonstrate that compared to existing state-of-the-art schemes, our scheme can significantly boost the anti-steganalysis capability.

JPEG Reversible data hiding (RDH) aims at correctly extracting hidden data and perfectly recovering the original JPEG image. By combining different frequency selection and block ordering manners, appropriate AC coefficients can be determined to achieve an efficient JPEG RDH scheme using histogram shifting (HS) mechanism. Nevertheless, existing methods only rely on rough frequency band distortion model by involving all DCT blocks, ignoring the dynamic influence of block ordering on embedding block selection. As a result, JPEG image containing hidden data may have an obvious distortion and file size expansion due to an inappropriate frequency band selection. To address the aforementioned problem, we design a new JPEG RDH scheme to optimize distortion model with frequency priority reassignment. Our method firstly orders all DCT blocks by referring to zero AC coefficients of each block. Subsequently, based on the given secret data, only partial ordered blocks are selected to calculate the distortion of each DCT frequency, which can further optimize unit distortion caused by shiftable coefficients. Furthermore, we employ the adjustment parameter to adaptively reassign the priority of each frequency band based on its influence on file size expansion, which can significantly reduce file size expansion of the marked JPEG image. Extensive experiments demonstrate that our method outperforms existing JPEG RDH methods with better visual quality and smaller file size increment of the marked image.

Secret sharing is a useful method which divides a secret message into several shares for security. During the recovery procedure, only when sufficient shares are obtained, the secret message can be recovered. This paper proposes two novel reversible data hiding schemes in encrypted image via secret sharing over Galois fields${{GF}}{({p})}$and${{GF}}{(}{{2}^{{8}}}{)}$. The content owner first applies a specific encryption method through block and pixel permutation and Shamir’s secret sharing. Then, the theoretical demonstration is introduced to explain that the generated shares are suitable for data embedding over${{GF}}{({p})}$and${{GF}}{(}{{2}^{{8}}}{)}$. Finally, two embedding algorithms over${{GF}}{({p})}$and${{GF}}{(}{{2}^{{8}}}{)}$are presented, and on the receiver side, with different keys, additional data can be extracted correctly and original image can be recovered losslessly. Experimental results show that our schemes can achieve better rate-distortion performance than some state-of-the-art schemes.

Reversible data hiding in encrypted images (RDHEI), an essential branch of reversible data hiding (RDH), has been in development for more than a decade. For most existing stream-cipher-based RDHEI algorithms, encryption schemes are often not the same; thus, these schemes have different effects on the encrypted images. As a result, it is not reasonable to compare the embedding rates (ERs) of RDHEI algorithms directly as we do for plaintext RDH algorithms. However, to our knowledge, many studies focus on the performance of embedding but neglect the influence of the encryption. To compare the performance of stream-cipher-based RDHEI algorithms more reasonably, this paper proposes a novel comprehensive measure to evaluate state-of-the-art RDHEI algorithms. First, the characteristics of the stream-cipher-based RDHEI algorithms are divided into two categories according to the encryption and embedding processes. Next, we use correlation and redundancy to evaluate the influence of encryption schemes and also use ER, computation complexity, visual quality, and algorithm stability to evaluate the embedding schemes. In the end, in order to combine all six indexes into the final evaluation measure, we standardize each index before applying the radar chart. The experimental results show the evaluation results of the recent RDHEI algorithms via a comprehensive analysis and demonstrate the guiding significance of the proposed method for the current RDHEI algorithm selection.

In recent decades, a large number of perceptual image hashing schemes have been designed to secure the authenticity and integrity of digital images. However, the feasible criterion to evaluate the performances of hashing schemes has not been developed yet. To this end, a unified performance evaluation method for perceptual image hashing schemes is proposed in this paper. The proposed evaluation method contains six modules: robustness, discrimination, tampering detection, security, computational efficiency and hash length. The order relationship analysis (ORA) is employed to assign the score proportion of each module in accordance with the relative importance of performance, which allows the customizability of user. The real scores of modules and the outputted final score can reflect the performances of perceptual image hashing schemes intuitively and convincingly. Experimental results demonstrate that the proposed evaluation method is practical and effective for the complete and comprehensive evaluation of perceptual image hashing schemes.

Most computer vision algorithms require parameter adjustment according to the image noise level. Conventionally, the additive white Gaussian noise (AWGN) model is widely used in most noise estimation algorithms; however, this assumption does not hold in the real world where the noise from cameras is more complex, and it is more appropriate to assume the signal-dependent noise (SDN) model. In this paper, we focus on the SDN model while considering the nonlinear radiometric calibration inside an actual camera, and propose an algorithm to efficiently estimate the noise level function (NLF), which is defined as the noise standard deviation with respect to image intensity. First, the input image is divided into overlapping patches, and noise samples are estimated in the linear transform domain. The confidence levels of the noise samples and the prior of the camera response function are then employed as constraints for the recovery of the NLF. Finally, the noise samples and constraints are represented in a convex optimization problem. The experimental results using both real and synthetic noisy images demonstrate the superiority of the proposed method. In addition, the estimated NLFs are incorporated into two well-known denoising schemes, non-local means and BM3D, and shows significant improvements in denoising SDN-polluted images.

As the deep hashing technique has been widely used in large-scale image retrieval, the corresponding security issue is getting more and more attention. Recent studies have found that deep image classifiers are vulnerable to adversarial example attacks and produce misleading classifications. Therefore, in order to study the robustness of deep hashing based retrieval system to adversarial example, in this letter, we propose a novel adversarial example generation algorithm, non-targeted deep hashing attack (NDHA), which uses the anchor-moving strategy to continuously modify anchor image to cross the search correlation boundary and maximize Hamming distance between the hash codes of adversarial example and query image. The generated adversarial example can make the retrieved result semantically irrelevant to query image. Extensive experiments show that the proposed NDHA can efficiently produce imperceptible perturbation, which is effective for attacking deep hashing based retrieval systems.

In this paper, a novel perceptual image hashing scheme based on convolutional neural network (CNN) with multiple constraints is proposed, in which our deep hashing network learns the process of features extraction automatically according to the training target and then generates the final hash sequence. The combination of convolutional and pooling layers is to reduce the size of input image while deepening the channels. Then, we construct two pairs of constraints and integrate them into an overall constraint function through a strategy of weight allocation. In order to guarantee the robustness and discrimination of deep hashing network simultaneously, a new training method is developed to adjust the training set structure dynamically according to the changes of constraint values. Experimental results show that the proposed deep hashing network can achieve a satisfactory balance between perceptual robustnzess and discrimination while maintaining security. Based on the large-scale test set, receiver operating characteristic (ROC) curves,${F}_{1}$scores and equal error rate (EER) demonstrate the superiority of our scheme in terms of content authentication compared with some state-of-the-art schemes.

The precise estimation of the noise level is a crucial issue in image processing. In this study, the authors propose a new method for noise standard deviation (STD) estimation from natural images based on skewness‐scale invariance in the transform domain and an adaptive noise injection strategy. The method is divided into two steps. The first step assumes that the natural clean image has the property of constancy of skewness in the transform domain. Then, a preliminary noise estimation method based on skewness invariance is designed by solving a constrained non‐linear optimisation problem. The second step involves noise rectification via noise injection. According to the phenomenon that compared with the high‐noise circumstance, the error of preliminary estimation is more serious under a low amount of noise, the noise STD is re‐estimated by injecting another noise for which the STD is known. In addition, the threshold model with respect to image complexity is established to identify whether a second estimation is needed. The experimental results demonstrate the efficacy of the proposed method and performance is superior to other state‐of‐the‐art methods.

Considering that traditional image steganography technologies suffer from the potential risk of failure under lossy channels, an enhanced adaptive steganography with multiple robustness against image processing attacks is proposed, while maintaining good detection resistance. First, a robust domain constructing method is proposed utilizing robust element extraction and optimal element modification, which can be applied to both spatial and JPEG images. Then, a robust steganography is proposed based on “Robust Domain Constructing + RS-STC Codes,” combined with cover selection, robust cover extraction, message coding, and embedding with minimized costs. In addition, to provide a theoretical basis for message extraction integrity, the fault tolerance of the proposed algorithm is deduced using error model based on burst errors and decoding damage. Finally, on the basis of parameter discussion about robust domain construction, performance experiments are conducted, and the recommended coding parameters are given for lossy channels with different attacks using the analytic results for fault tolerance. A series of experimental results demonstrate that the proposed algorithm can extract embedded messages with significantly higher accuracy after different attacks, such as compression, noising, scaling and other attacks, compared with the state-of-the-art adaptive steganography, and robust watermarking algorithms, while maintaining good detection resistant performance.

In this paper, a novel lossy compression scheme for encrypted image based on image inpainting is proposed. In order to maintain confidentiality, the content owner encrypts the original image through a modulo-256 addition encryption and block permutation to mask image content. Then, the third party, such as a cloud server, can compress the selective encrypted image before transmitting to the receiver. During compression, encrypted blocks are categorized into four sets corresponding to different complexity degrees in plaintext domain without the loss of security. By allocating various bit rates to the encrypted blocks from different sets, flexible compression can be achieved with difference quantization. After parsing and decoding the compressed bit stream, the receiver first recovers partial encrypted pixels and then decrypts them. The other missing pixels are further recovered with the assistance of image inpainting based on a total variation model, and the final reconstructed image can be produced. Experimental results demonstrate that the proposed scheme achieves better rate-distortion performance than some of the state-of-the-art schemes.

Abstract Embedding secret data in vector quantization (VQ) compressed images with reversibility has been studied extensively in recent years. However, to date, the reported methods have not achieved satisfactory performances of hiding capacity and image compression ratio simultaneously. In this paper, we propose a reversible embedding method based on search‐order coding (SOC) and index parity matching that can hide secret data into the compressed VQ index, that is, SOC index. If the parity of the candidate SOC index matches the current embedding bit and the error caused by SOC encoding is smaller than a pre‐determined threshold, the length of the stego SOC index after embedding is significantly shorter than the original VQ index. On the receiver side, the embedded secret bits can be easily extracted by checking the parity of stego SOC indices, and all original VQ indices can be recovered correctly. Experimental results demonstrate that our method can achieve greater hiding capacity than the recently reported methods for the same image decompression quality. Copyright © 2014 John Wiley & Sons, Ltd.

In this paper, we propose a novel joint data-hiding and compression scheme for digital images using side match vector quantization (SMVQ) and image inpainting. The two functions of data hiding and image compression can be integrated into one single module seamlessly. On the sender side, except for the blocks in the leftmost and topmost of the image, each of the other residual blocks in raster-scanning order can be embedded with secret data and compressed simultaneously by SMVQ or image inpainting adaptively according to the current embedding bit. Vector quantization is also utilized for some complex blocks to control the visual distortion and error diffusion caused by the progressive compression. After segmenting the image compressed codes into a series of sections by the indicator bits, the receiver can achieve the extraction of secret bits and image decompression successfully according to the index values in the segmented sections. Experimental results demonstrate the effectiveness of the proposed scheme.

In this paper, we propose a novel prediction-based reversible steganographic scheme based on image inpainting. First, reference pixels are chosen adaptively according to the distribution characteristics of the image content. Then, the image inpainting technique based on partial differential equations is introduced to generate a prediction image that has similar structural and geometric information as the cover image. Finally, by using the two selected groups of peak points and zero points, the histogram of the prediction error is shifted to embed the secret bits reversibly. Since the same reference pixels can be exploited in the extraction procedure, the embedded secret bits can be extracted from the stego image correctly, and the cover image can be restored losslessly. Through the use of the adaptive strategy for choosing reference pixels and the inpainting predictor, the prediction accuracy is high, and more embeddable pixels are acquired. Thus, the proposed scheme provides a greater embedding rate and better visual quality compared with recently reported methods.

Reversible/lossless image data hiding schemes provide the capability to embed secret information into a cover image where the original carrier can be totally restored after extracting the secret information. This work presents a high performance reversible image data hiding scheme especially in stego image quality control using image inpainting, an efficient image processing skill. Embeddable pixels chosen from a cover image are initialized to a fixed value as preprocessing for inpainting. Subsequently, these initialized pixels are repaired using inpainting technique based on partial differential equations (PDE). These inpainted pixels can be used to carry secret bits and generate a stego image. Experimental results show that the proposed scheme produces low distortion stego images and it also provides satisfactory hiding capacity.

A copyright management system for online trade of digital images is proposed in which low-resolution images with a visible mark are freely downloadable. An authorized user receives a package containing the details of the image he/she buys together with a key for mark removing. Using a downloaded client-end routine, the user removes the mark, reconstructs the high-quality image and embeds a robust fingerprint in the image simultaneously.