System software architectures, such as assemblers, require synchronous maintenance as Instruction Set Architectures (ISAs) continuously evolve. These software systems typically feature dedicated, specialized implementations for each ISA. However, the fragmentation of data structures and implementation styles across distinct ISAs complicate performance optimization, rendering these optimizations non-portable, and introduce systemic challenges for rigorous performance analysis. Analogous issues also plague software like compiler backends.To address this challenge, we propose the Scalable Assembler System (SAS). SAS enables the reuse of ISA-agnostic modules by unifying its core data structures and procedural definitions. The SAS architecture, through the standardization of key data structures like instruction descriptors and unified workflow, decouples the core stages of the assembly process from ISAspecific designs. This separation allows performance analysis and optimization methodologies to be systematically applied across the entire assembly architecture.We have implemented a prototype system in the Rust language supporting AMD64, AArch64, and RISC-V64. Performance analysis to this prototype initially indicates that it exhibits a statistically significant performance advantage over GNU AS. Our quantitative analysis shows that integrating SAS into the compilation pipeline can yield approximately $1 \%$ performance improvement. We believe that the design experience of SAS and its unified methodology for performance analysis hold promise for further generalization to the architecture and optimization of other system software.

A community-imbalanced graph refers to a graph containing multiple communities with large differences in node and edge scales. Graph sampling is a widely used graph reduction technique to accelerate graph computations and simplify graph visualizations. However, existing graph sampling algorithms may encounter several problems, including the loss of small communities, disconnections between communities, and distortions of community scale distribution, on maintaining the community structures in a community-imbalanced graph. In this work, a new quality indicator is proposed to determine if a graph can be regarded as a community-imbalanced graph. A community-imbalanced graph sampling (CIGS) algorithm is proposed to address the community-imbalanced graph sampling problems. Three new evaluation metrics are proposed to assess the performance of community structure maintenance of graph sampling. An algorithm performance experiment and a user study are conducted to evaluate the effectiveness of the proposed CIGS.

Image Steganography without Embedding (SWE) is an emerging data hiding paradigm. Instead of embedding a secret message into a container image, SWE synthesises a novel image by using the secret message as a latent code. Current SWE methods have achieved high synthesis quality and strong resistance to steganalysis tools. However, it remains challenging to apply the SWE due to two reasons: (i) lack of synthesis diversity and (ii) recovery of secret messages under malicious image attacks. In this paper, we present a novel SWE framework with a disentanglement autoencoder to tackle the above challenges. Specifically, the autoencoder disentangles an image into a structure and texture representation. Then, we exploit the stability of the structure representation to improve secret message recovery reliability, while increasing synthesis diversity by randomising texture representations and employing a chaotic system for structure randomisation to enhance its security. To further achieve a robust message recovery under malicious attacks, an adversarial learning strategy is introduced into our framework, which guarantees high recovery accuracy. Our method outperforms other state-of-the-art SWE methods in terms of synthesis quality, synthesis diversity and secret message recovery accuracy under various image attacks. The source code is publicly available athttps://github.com/Lemok00/RDI-SWE.

Unauthorised face recognition (FR) systems have posed significant threats to digital identity and privacy protection. To alleviate the risk of compromised identities, recent makeup transfer-based attack methods embed adversarial signals in order to confuse unauthorised FR systems. However, their major weakness is that they set up a fixed image unrelated to both the protected and the makeup reference images as the confusion identity, which in turn has a negative impact on both attack success rate and visual quality of transferred photos. In addition, the generated images cannot be recognised by authorised FR systems once attacks are triggered. To address these challenges, in this paper, we propose a Recoverable Makeup Transferred Generative Adversarial Network (RMT-GAN) which has the distinctive feature of improving its image-transfer quality by selecting a suitable transfer reference photo as the target identity. Moreover, our method offers a solution to recover the protected photos to their original counterparts that can be recognised by authorised systems. Experimental results demonstrate that our method provides significantly improved attack success rates while maintaining higher visual quality compared to state-of-the-art makeup transfer-based adversarial attack methods. Our code and supplementary materials are available on Github.

Achieving fairness in clinical AI remains challenging due to class bias in long-tailed datasets. We propose Class wise Fair Test-time Adaptation (CFTA), a pragmatic setting where biased pre-trained models are adapted to single test instances without source data. To this end, we introduce FairBN, which hierarchically recalibrates BatchNorm statistics through three modules: Instance-Specific Adaptation (ISA), Memory Bank Maintenance (MBM), and Class-Aware Calibration (CAC). Experiments on four medical benchmarks show that FairBN consistently outperforms recent TTA methods (TENT, CoTTA, RoTTA), achieving notable improvements in both accuracy and class-wise F1 fairness.

Vascular segmentation in medical images is crucial for disease diagnosis and surgical navigation. However, the segmented vascular structure is often discontinuous due to its slender nature and inadequate prior modeling. In this paper, we propose a novel Serpentine Window Mamba (SWinMamba) to achieve accurate vascular segmentation. The proposed SWinMamba innovatively models the continuity of slender vascular structures by incorporating serpentine window sequences into bidirectional state space models. The serpentine window sequences enable efficient feature capturing by adaptively guiding global visual context modeling to the vascular structure. Specifically, the Serpentine Window Tokenizer (SWToken) adaptively splits the input image using overlapping serpentine window sequences, enabling flexible receptive fields (RFs) for vascular structure modeling. The Bidirectional Aggregation Module (BAM) integrates coherent local features in the RFs for vascular continuity representation. In addition, dual-domain learning with Spatial-Frequency Fusion Unit (SFFU) is designed to enhance the feature representation of vascular structure. Extensive experiments on three challenging datasets demonstrate that the proposed SWinMamba achieves superior performance with complete and connected vessels.

Class Incremental Learning (CIL) aims to enable models to continuously learn new categories while retaining previous classification abilities. In medical scenarios, where new disease categories frequently emerge, CIL becomes crucial. Traditional CIL approaches often face "catastrophic forgetting". Analytical Class Incremental Learning (ACIL) offers an analytical (i.e., closed-form) linear solution that does not depend on conventional replay or regularization techniques, thereby mitigating forgetting and addressing privacy concerns, making it suitable for medical datasets. However, few studies have explored the problem of knowledge forgetting in CIL for medical data with ACIL. Based on the latest research, we systematically study this problem for the first time. Specifically, we present a benchmark named AIDC (Analytical Incremental Disease Classification), comparing ACIL against five established CIL methods across three medical datasets. Results show that ACIL achieves notably higher average classification accuracy and exhibits better anti-forgetting capabilities compared to traditional methods.

Source-Free Domain Adaptation (SFDA) aims to train a target model without source data, and the key is to generate pseudo-labels using a pre-trained source model. However, we observe that the source model often produces highly uncertain pseudo-labels for hard samples, particularly those heavily affected by domain shifts, leading to these noisy pseudo-labels being introduced even before adaptation and further reinforced through parameter updates. Additionally, they continuously influence neighbor samples through propagation in the feature space. To eliminate the issue of noise accumulation, we propose a novel Progressive Curriculum Labeling (ElimPCL) method, which iteratively filters trustworthy pseudo-labeled samples based on prototype consistency to exclude high-noise samples from training. Furthermore, a Dual MixUP technique is designed in the feature space to enhance the separability of hard samples, thereby mitigating the interference of noisy samples on their neighbors. Extensive experiments validate the effectiveness of ElimPCL, achieving up to a 3.4% improvement on challenging tasks compared to state-of-the-art methods.

In this paper, a robust Bayesian learning-based optimization algorithm is proposed to improve the performance of power allocation in wireless communications, addressing the problem of deep learning in wireless communications, which is unable to effectively quantify uncertainty. Specifically, by analyzing model uncertainty and aleatoric uncertainty in wireless communications, and combining model ensemble and power-constrained loss methods, a variational autoencoder power allocation algorithm (VAPA) is designed to reduce the impact of uncertainty on the optimization process significantly. Experimental results show that VAPA can effectively deal with model mismatches and outliers, significantly reducing the average power output while maintaining the communication rate. This study provides a new solution to the optimization problem in wireless communications that can facilitate the use of deep learning in communication scenarios with high reliability requirements.

For the optimal power allocation problem in interference networks, traditional methods exhibit high computational complexity, while deep learning-based methods often underutilize domain knowledge. To address these challenges, we propose a novel approach termed Weighted Minimum Mean Square Error (WMMSE) full unfolding-based graph neural networks (FUWMMSE). This method integrates key modeling elements from traditional approaches with data-driven components of deep learning, employing the concept of deep unfolding-based methods. Specifically, by unfolding the iterative WMMSE method, optimizing hyperparameters, designing a graph neural networks (GNNs) network structure, augmenting modeling elements with GNNs, and leveraging the strengths of both model-based and data-based methods, our proposed neural network architecture is formulated. This design aims to overcome the limitations of insufficient domain knowledge utilization, complex computational structures, and poor generalization abilities observed in current unfolding-type methods. Theoretical analysis demonstrates that our method possesses the desirable properties of permutation equivariance, ensuring both interpretability and generalizability. Extensive numerical experiments validate that the FUWMMSE method has better performance and generalization capability than other unfolding class methods while maintaining a fast convergence speed.

Machine learning-based Android malware detection has consistently demonstrated superior results. However, with the continual evolution of the Android framework, the efficacy of the deployed models declines markedly. Existing solutions necessitate frequent and expensive model retraining to resist the constant evolution of malware accompanying Android framework updates. To address this, we introduce a solution called ASDroid, which generalizes specific APIs into similar API clusters to counteract evolving Android malware threats. One primary challenge lies in identifying analogous API clusters that correspond to specific APIs. Our approach involves extracting semantic information from open-source API source code to construct a heterogeneous information graph, and utilizing embedding algorithms to obtain semantic vector representations of APIs. APIs that are close in embedding distance are presumed to have similar semantics. Our dataset encompasses Android applications spanning nine years from 2011 to 2019. In comparison to existing Android malware detection model aging mitigation solutions like APIGraph, SDAC and MaMaDroid, ASDroid demonstrates greater accuracy and more effective at resisting continuously evolving malware.

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

Computed tomography (CT) scans are clinically important in radiotherapy planning (RTP) for ROI contour delineation and radiation dose calculation. However, it involves significant radiation exposure, which can bring potential health problems. Nowadays, the synthesis of MR to CT provides an alternative to repetitive CT examinations. Although transformers are widely used for image synthesis, achieving effective multi-regions pseudo-CT synthesis from magnetic resonance (MR) images faces common and unique challenges: 1) The quadratic time complexity problem. While transformer facilitates long-range modeling in image synthesis, efficiently integrating the self-attention mechanism with 3D volume data remains an unresolved challenge. 2) The modal differences between MR and CT are significant, and the complex structural priors present within MR and CT make it difficult for transformer to learn effective mapping functions. To address these issues, we propose a high frequency-information guided net for multi-regions pseudo-CT synthesis (HFGS), efficiently generating multi-regions pseudo-CTs from different MR sequences. Our carefully designed 3D cascaded frequency transformer (CFT) serves as the synthesis module, utilizing element-wise product of frequency domain signals instead of matrix multiplication in spatial domain. This approach provides an efficient self-attention calculation method and improves synthesis efficiency. Additionally, to tackle the challenge of insufficient high-frequency information for high-quality decoding, we have designed a learnable guidance module to capture important structural priors within both the source and target modalities, guiding the synthesis module to produce high-quality pseudo-CTs. Our code will be available at https://github.com/qijianyu277/HFGS.

Face forgery detection has recently progressed to address the threat from image synthesis technology, although robust face forgery detection under heterogeneous attacks remains challenging. When forgers leverage image post-processing techniques to manipulate forged photos, recent detection methods exhibit significant performance degradation. In this work, we propose a novel multi-strategy adversarial learning (MAL) method to extract salient features in order to achieve more reliable forgery detection under attacks. In particular, our MAL framework creates a large number of positive and negative sample pairs by designing a composite attack generation module with supervised contrastive training to ensure the attack robustness. In addition, we exploit two intuitive strategies, hard sample selection and region consistency, to enhance the contrastive losses for further strengthened feature reliability. Extensive experimental results demonstrate our proposed method to outperform recent state-of-the-art face forgery detection methods in terms of overall accuracy under various single and composite attacks.

Noisy data is ubiquitous in quantum computer, greatly affecting the performance of various algorithms. However, existing quantum support vector machine models are not equipped with anti-noise ability, and often deliver low performance when learning accurate hyperplane normal vectors from noisy data. To attack this issue, an anti-noise quantum support vector machine algorithm is developed in this paper. Specifically, a weight factor is first embedded into the hinge loss, so as to construct the objective function of anti-noise support vector machine. And then, an alternative iterative optimization strategy and a quantum circuit are designed for solving the objective function, aiming to obtain the normal vector and intercept of the hyperplane that finally divides the data. Finally, the classification and anti-noise effect of the algorithm are verified on artificial dataset and public dataset. Experimental results show that the proposed algorithm is efficient, yet maintains stable accuracy in noisy data.

The KNN (K-nearest neighbors) algorithm is one of Top-10 data mining algorithms and is widely used in various fields of artificial intelligence. This leads to that quantum KNN algorithms have developed and achieved certain speed improvements, denoted as Q-KNN. However, these Q-KNN methods must face two key problems as follows. The first one is that they are mainly focused on neighbor selection without paying attention to the influence of K value on the algorithm. The second is that only the neighbor selection process is quantized, and the selection of K value is not quantized. To solve these problems, this paper designs a novel quantum circuit for KNN classification, so as to simultaneously quantumize the neighbor selection and K value selection process. Specifically, the least squares loss and sparse regularization term are first used to construct the objective function of the proposed quantum KNN, so that it can simultaneously obtain the optimal K value and K nearest neighbors of the testing data. And then, a new quantum circuit is proposed to quantumize the process through quantum phase estimation, controlled rotation, and inverse phase estimation techniques. Finally, experiments are conducted with qiskit and matlab to output the quantum and classical results of the algorithm, verifying that the proposed algorithm can output the optimal K value and K nearest neighbors for each testing data.

Recommendation has become especially crucial during the COVID-19 pandemic as a significant number of people rely on online shopping from home. Existing recommendation algorithms, designed to address issues like cold start and data sparsity, often overlook the time constraints of users. Specifically, users expect to receive recommendations for products of interest in the shortest possible time. To address this challenge, we propose a novel collaborative filtering recommendation algorithm that leverages the advantages of quantum computing circuits based on data reconstruction. This approach allows for the rapid identification of users similar to the target user, thereby improving recommendation speed. In our method, we utilize the information of known users to linearly reconstruct that of the target users, forming a relational matrix. Subsequently, we employ \(l_{2,1}-\) norm and \(l_{1}-\) norm to sparsely constrain the relationship matrix, deducing the weight of each known user. The final step involves providing similar recommendations to target users based on these weights. Furthermore, we implement the proposed algorithm using a quantum circuit, enabling exponential acceleration. The final weight matrix is derived from the quantum state outputted by the circuit. The speed of this process is theoretically demonstrated in detail. Experimental results indicate that our algorithm outperforms state-of-the-art methods in terms of root mean squared error (RMSE), mean absolute error (MAE) and normalized discounted cumulative gain (NDCG). Compared to state-of-the-art comparison algorithms, the proposed algorithm achieves the fastest recommendation speed across eight public datasets.

Reference-based image super-resolution (RefSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) images by introducing HR reference images. The key step of RefSR is to transfer reference features to LR features. However, existing methods still lack an efficient transfer mechanism, resulting in blurry details in the generated image. In this article, we propose a double-layer search module and an adaptive pooling fusion module group for reference-based image super-resolution, called DLASR. Based on the re-search strategy, the double-layer search module can produce an accurate index map and score map. These two maps are used to filter out accurate reference features, which greatly increases the efficiency of feature transfer in the later stage. Through two continuous feature-enhancement steps, the adaptive pooling fusion module group can transfer more valuable reference features to the corresponding LR features. In addition, a structure reconstruction module is proposed to recover the geometric information of the images, which further improves the visual quality of the generated image. We conduct comparative experiments on a variety of datasets, and the results prove that DLASR achieves significant improvements over other state-of-the-art methods, in terms of quantitative accuracy and qualitative visual effect. The code is available at https://github.com/clttyou/DLASR.

Discovering visual evidence is of great importance in making glaucoma diagnosis trustworthy, with interpretable processes and reliable results. Existing works usually learn image representation for glaucoma diagnosis, where the cup-to-disc ratios (CDRs) are employed as the quantitative evidence to interpret the diagnosis model. However, they rely on global visual features which are insufficient for the trustworthy interpretation of medical image for disease diagnosis. To enable interpretable and reliable glaucoma diagnosis, this paper proposes confidence-guided weakly-supervised learning (CG-WSL) by exploiting the intrinsic visual-semantic interactions in fundus images. The CG-WSL discovers the evidential local regions to support the reliable glaucoma diagnosis with fine-grained anatomical representations, only given the image-level annotations. The evidential local regions not only provide the localization information about the lesions and anatomies for visual interpretation, but also enhance the feature presentation with fine-grained anatomy-level features to discriminate the abnormal cases. Specifically, it consists of two parts: confidence-guided evidence discovery (CGED) for multi-scale fine-grained visual evidence discovery, and feature weighted fusion (FWF) for coarse-to-fine grained representation learning. Experimental results on two datasets demonstrate the effectiveness of proposed method on glaucoma diagnosis with accuracy of 0.981 (LAG) and 0.956 (RIM-ONE r2). Visualization results indicate the visual evidence for glaucoma diagnosis, which makes the diagnosis process interpretable and results reliable.

Most of the existing unsupervised domain adaptive object detection methods are based on twostage object detectors such as Faster-RCNN because the region proposal network(RPN) module, which onestage detectors don’t have, can help the model achieve instance-level local domain adaption. Although this type of methods have good detection accuracy, the real-time performance cannot meet the requirements of scenarios such as autonomous driving. To this end, we propose a self-attention domain adaptive network suitable for the one-stage detector YOLOv7, which performs the self-attention to extract the position information related to the foreground target as RPN to do instance-level local domain adaptation. At the same time, we also propose a local self-attention augmentation method to suppress the attention noise so that the model can pay attention to the foreground target accurately. Considering the fact that the detection ability of model is from weak to robust during training, we apply coarse-to-fine alignment that global domain adaptation first aligns the the global feature coarsely and transferring to local domain adaptation gradually to finely align the local feature of the foreground target. Our proposed method is validated on Cityspaces, Foggy Cityspaces, KITTI and Sim10K datasets, outperforming existing domain adaptive object detection methods.

Adversarial attacks reveal the inherent vulnerability of deep neural networks, which face serious security issues for their security. Among them, the attack against the Deep Neural Network (DNN) application used in the Industrial Internet of Things (IIoT) is a key area in adversarial attacks. Adversarial examples generated by attackers by adding human-undetectable interference to legitimate examples may cause models to make wrong decision results, resulting in serious accidents. Many detection technologies have been proposed to mitigate the harm of adversarial examples to neural networks, among which the methods based on the difference of feature attribution between normal examples and adversarial examples show state-of-the-art detection performance, but they suffer from detection efficiency. In this work, we focus on improving the detection efficiency of the feature-attribution-based detection methods. We observe that there is still a significant difference in the feature attribution distribution of a normal image and an adversarial image even only some pixels in the image are processed, which can be verified by utilizing the Kolmogorov-Smirnov test. Based on this observation, we first adopt a variety of strategies to sample partial pixels in an image and then utilize the selected pixels to train a feature-attribution-based detector for detecting adversarial examples. Extensive experiments conducted on four datasets (MNIST, CIFAR-10, SVHN, CIFAR-100) against various attacks proved that the detection efficiency of the accelerated detection method is improved (for example, the average execution time was increased by 8.7 times on CIFAR-10) while the detection performance maintains state-of-the-art.

Recently there has been many studies on backdoor attacks, which involve injecting poisoned samples into the training set in order to embed backdoors into the model. Existing multiple poisoned samples attacks usually randomly select a subset from clean samples to generate the poisoned samples. Filtering-and-Updating Strategy (FUS) has shown that the poisoning efficiency of each poisoned sample is inconsistent and random selection is not optimal. However, FUS does not fully considered the selection of multiple poisoned samples, there are still some issues with the selection of multiple poisoned samples. In this paper, we formulate the selection of multiple types of poisoned samples as a multi-objective optimization problem and proposed a Multiple Poisoned Samples Selection Strategy (MPS) to solve the issue. Unlike FUS, we consider the potential of clean samples that are not selected as to become efficient poisoned samples. Specifically, we use a weight-based contribution approach to calculate the contribution of each sample (clean sample and poisoned sample) during the training process from multiple dimensions. Finally, based on the greedy approach, we retain a subset of samples with the largest contribution in each dimension through iterations. We evaluate the effectiveness of MPS on various attack methods, including BadNet, Blended, ISSBA, and WaNet, as well as benchmark datasets. The experimental results on CIFAR-10 and GTSRB show that MPS can increase the attack strength by 1.45% to 18.34% compared to RSS and 0.43% to 10.84% compared to FUS in multiple poisoned samples attacks, thereby enhancing the stealthiness of the attack. Meanwhile, MPS is suitable for black-box settings, meaning that poisoned samples selected in one setting can be applied to other settings.

Neuronal feature visualization is widely used in Explainable Artificial Intelligence (XAI). It can provide an intuitive visualization to depict the feature extraction of an individual neuron in a Convolutional Neural Network (CNN). However, it is extremely exhaustive for human users to identify highly interpretable visualizations by manually browsing massive neurons contained in a CNN. Inspired by the Shapley Value Method in coalitional game theory, this paper proposes a metric to quantitatively measure the interpretability of a neuronal feature visualization by calculating the similarity between the SHAP (SHapley Additive exPlanation) image and the visualization. This metric can help human users quickly find highly interpretable neuronal feature visualizations for understanding the classification results of a CNN.

Abstract Face swapping is a technique that replaces a face in a target media with another face of a different identity from a source face image. Currently, research on the effective utilisation of prior knowledge and semantic guidance for photo‐realistic face swapping remains limited, despite the impressive synthesis quality achieved by recent generative models. In this paper, we propose a novel conditional Denoising Diffusion Probabilistic Model (DDPM) enforced by a two‐level face prior guidance. Specifically, it includes (i) an image‐level condition generated by a 3D Morphable Model (3DMM), and (ii) a high‐semantic level guidance driven by information extracted from several pre‐trained attribute classifiers, for high‐quality face image synthesis. Although swapped face image from 3DMM does not achieve photo‐realistic quality on its own, it provides a strong image‐level prior, in parallel with high‐level face semantics, to guide the DDPM for high fidelity image generation. The experimental results demonstrate that our method outperforms state‐of‐the‐art face swapping methods on benchmark datasets in terms of its synthesis quality, and capability to preserve the target face attributes and swap the source face identity.

Lip reading can help people with speech disorders to communicate with others and provide them with a new channel to interact with the world. In this paper, we design and implementHearMe, an accurate and real-time lip-reading system built on commercial RFID devices. HearMe can be used to accurately recognize different words in a pre-defined vocabulary without limitations in light conditions and can be used in multiple user scenarios by leveraging RFID's ability in identifying different users. We design an effective data collection strategy to well capture the tiny and complex signal patterns caused by mouth motion and propose a set of algorithms to extract signal profiles related to mouth motions and mitigate interference factors like multi-path. A carefully designed set of features, including time-domain statistical features and frequency-domain features, are then extracted from the signal to lift the recognition accuracy at the word level. To reduce training costs when the model is used in a new environment, a transfer-learning-based approach is adopted to enhance the robustness of the model in cross-environment scenarios. Experimental results show that HearMe detects speaking actions of the user with an accuracy higher than 0.95 and recognizes different words in a 20-words vocabulary with an average accuracy higher than 0.88. Moreover, the latency of HearMe ($\sim$150ms) is nearly two orders of magnitude less than traditional approaches, making it applicable to practical scenarios that require real-time lip reading.

Conventional steganography approaches embed a secret message into a carrier for concealed communication but are prone to attack by recent advanced steganalysis tools. In this paper, we propose Image DisEntanglement Autoencoder for Steganography (IDEAS) as a novel steganography without embedding (SWE) technique. Instead of directly embedding the secret message into a carrier image, our approach hides it by transforming it into a synthesised image, and is thus fundamentally immune to typical steganalysis attacks. By disentangling an image into two representations for structure and texture, we exploit the stability of structure representation to improve secret message extraction while increasing synthesis diversity via randomising texture representations to enhance steganography security. In addition, we design an adaptive mapping mechanism to further enhance the diversity of synthesised images when ensuring different required extraction levels. Experimental results convincingly demonstrate IDEAS to achieve superior performance in terms of enhanced security, reliable secret message extraction and flexible adaptation for different extraction levels, compared to state-of-the-art SWE methods.

The human can easily recognize the incongruous parts of an image, for example, perturbations unrelated to the image itself, but are poor at spotting the small geometric transformations. However, in terms of the robustness of deep neural networks (DNNs), the ability to properly recognize objects with small geometric transformations is still a challenge. In this work, we investigate the problem from the perspective of adversarial attacks: does the performance of DNNs degrade even when small geometric transformations are applied to images? To this end, we propose a novel adversarial attack method, called WBA, a Warping-Based Adversarial attack method, which does not introduce information independent of the original images but manipulates the existing pixels of the images by elastic warping transformations to generate adversarial examples that are imperceptible to the human eye. At the same time, existing adversarial attacks typically generate adversarial examples by modifying pixels in the spatial domain of the image, the addition of such perturbations introduces extra information unrelated to the image itself and is easily detected by the naked eyes. We demonstrate the effectiveness of WBA by extensive experiments on commonly used datasets, including MNIST, CIFAR10, and ImageNet. The results show that WBA can quickly generate adversarial examples with the highest adversarial strength, consumes less time, and can be comparable to optimization-based adversarial attack methods in image perception evaluation metrics such as LPIPS, SSIM, and far more than gradient direction-based iterative methods.

Exploring the characterization laws of image data and improving the efficiency of image data characterization knowledge is essential to promote the development of the Internet of Things technology. Considering that images in the real world usually contain multiple objects, and the objects are closely dependent. For these reasons, it brings great challenges to the robust representation learning of multilabel images. In general, researchers model the relationship between objects based on a class activation map and use graph convolution to mine the dependencies between objects. However, graph structure data often contain noise, which means that the edges between nodes are sometimes not so reliable, and the relative importance of neighbors is also different. Based on this, our goal is to reduce noisy connections and false connections between objects, eliminate multilabel image representation bias, and learn robust representations. Therefore, we propose a robust representation learning method for multilabel images driven by graph attention network (RRL-GAT). Specifically, to reduce the accidental false connection of objects in the image, we propose the class attention graph convolution module (C-GAT) to mine the strong association structure between categories. Besides, for the dynamic correlation between objects in the image, we propose an adaptive graph attention convolution module (A-GAT) to capture the subtle dynamic dependencies in the image. The results on two authoritative data sets show that our method is significantly better than all current state-of-the-art methods. Besides, the visualization results show that RRL-GAT can capture the semantic relationship of a specific input image and has sufficient recognizability.

Face images are typically a key component in the fields of security and criminal investigation. However, due to lighting and shooting angles, faces taken under low-light conditions are often difficult to recognize. Face super-resolution (FSR) technology can restore high-resolution faces based on low-resolution inputs. However, existing face super-resolution methods typically rely on prior knowledge of inaccurate faces estimated from low-resolution images. Faces restored by low-light inputs may suffer from problems such as low brightness and many missing details. In this article, we proposed an Illumination-Enhanced Face Super-Resolution (IEFSR) model that can progressively super-resolve low-light faces of 32 × 32 pixels by an upscaling factor of 8. While reconstructing the low-light low-resolution face into a clear and high-quality face, we introduce a coarse low-resolution (LR) restoration network to recover the LR face details hidden in the dark. In the generator, we use a series of style blocks with noise to make the generated faces appear to have a more realistic visual aesthetic. Additionally, we introduce spectrum normalization in the discriminator to improve training stability. Extensive experimental evaluations show that the proposed IEFSR yields visually and metrically more attractive results than existing state-of-the-art FSR methods.

Copyright protection of depth image-based rendering (DIBR) 3D videos is crucial due to the popularity of these videos. Despite the success of recent watermarking schemes, it is still challenging to ensure the robustness against strong geometric attacks when both lossless quality and distinguishability of protected videos are required. In this paper, we pro-pose a novel zero-watermarking scheme to improve the performance under strong geometric attacks when satisfying the other two requirements. In our scheme, CT-SVD-based features are extracted to ensure both distinguishability and robustness against signal processing and DIBR conversion at-tacks, while a SIFT-based rectication mechanism is designed to resist geometric attacks. Further, an attention-based fusion strategy is proposed to complement the robustness of rectied and unrectied CT-SVD features. Experimental results demonstrate that our scheme outperforms the existing zero-watermarking schemes in terms of distinguishability and robustness against strong geometric attacks such as rotation, cyclic translation and shearing.

How to use artificial intelligence technology to mine human abnormal behavior from considerable video data generated by the Internet-of-Things system has been intensively studied for a long time. Existing deep learning anomaly detection algorithms deployed in the cloud typically perform supervised learning based on constant kinds of abnormal behavior data. However, this supervised learning model with preset abnormal behavior categories ignores the diversity and unpredictability of abnormal occurrences in open scenarios. Thus, we propose an abnormal behavior detection algorithm as an edge network service by combining the advantages of cloud computing and the efficiency of edge networks. This method combines the double verification of global behavior detection and local fine-grained action cycle alignment to detect whether a behavior is abnormal. Moreover, to enable abnormal behavior detection models to predict test samples whose categories do not appear during the training stage, we propose an active label learning algorithm based on cycle clustering, which not only improves the efficiency of data transmission between the edge and the cloud but also makes model updates in the cloud more efficient. Extensive and quantitative experimental results show that our method can not only accurately detect abnormal human behavior at the edge of limited resources but also has strong robustness under the interference of test samples of unknown categories.

Millimeter-wave (mmWave) frequency bands, which offer abundant underutilized spectral resources, have been explored and exploited in the past several years to meet the requirements of emerging wireless services highlighted by high data rates, ultrareliability, and ultralow delivery latency. Yet, the unique characteristics of mmWave, e.g., continuous wide bandwidth, large path, and penetration losses, along with hardware constraints, call for innovative technologies for mmWave communication. Recently, an extensive amount of work on mmWave communication has been carried out by researchers and practitioners from both academia and industry, and various technologies have been developed for mmWave communication systems to fulfill the full potential of mmWave frequency bands. In this article, we present a comprehensive survey of the standardization of mmWave communication, the latest progress and outcomes of the research on mmWave communication technologies, and the emerging applications of mmWave communication. In particular, we provide a timely and in-depth summary of the state-of-the-art technology specifications of mmWave communication with an emphasis on the physical (PHY) layer. Then, we elaborate on a number of well-established or promising antenna architectures in mmWave communication systems and investigate the enabling PHY layer transmission technologies. Finally, we show some existing and emerging applications of mmWave communication and discuss the potential open research issues.

Summary In recent years, Cyber‐Physical Systems (CPS) and Artificial Intelligence (AI) have made good progress in the medical field. The medical CPS (MCPS) based on AI can realize the efficient and reasonable utilization of medical resources and improve the quality of medical process. However, current MCPS are still facing several challenges, and the privacy protection of medical data is one of the most critical challenges. Since medical data is stored in different hospitals, most studies collect data from decentralized hospitals to train a disease diagnosis model, which is not conducive to the privacy protection of patients. And in some existing solutions, it is also difficult for doctors to select the optimal model from multiple models in clinical diagnosis. In this paper, we propose a novel scheme based on federated learning in MCPS for training disease diagnosis models from distributed medical image data. Our scheme is divided into three parts: the model provider, the server, and the consumer, and a detailed working process is designed for each part. This scheme can not only effectively solve the problem of privacy protection, but also solve the problem of model selection for doctors and save storage space. It can ensure that consumers automatically get a steadily improved disease diagnosis model. This scheme is performed on simulated distributed medical image datasets. The experimental results show the effectiveness and superiority of our scheme.

Driven by the explosive growth of Internet of Things (IoT) devices with stringent requirements on latency and reliability, ultra-reliability and low latency communication (uRLLC) has become one of the three key communication scenarios for the 5th generation (5G) and 6G communication systems. In this paper, we focus on the beamforming design problem for the downlink multiuser uRLLC system. Since the strict demand on the reliability and latency, in general, short packet transmission is a favorable way for uRLLC systems, which indicates the classical Shannon’s capacity formula is no longer applicable. With the finite blocklength transmission, the achievable rate is greatly influenced by the reliability and finite blocklength. Using the developed achievable rate formula for finite blocklength transmission, we respectively formulate the problems of interest as the weighted sum rate maximization, energy efficiency maximization, and user fairness optimization by considering the maximum allowable transmission power and minimum rate requirement. These problems considered are non-convex and are hard to obtain the global optimal solution, even for the local optimal solution. To overcome these difficulties, some important insights have been discovered by analyzing the function of achievable rate. For example, an analytical solution of the minimum rate requirement is provided with respective to the signal-to-interference-plus-noise ratio. Based on the discovered results, we provide algorithms to optimize the beamforming vectors and power allocation, which are guaranteed to converge to a local optimum solution to the formulated problems with low computational complexity. Our simulation results reveal that our proposed beamforming algorithms outperform the zero-forcing beamforming algorithm with equal power or water filling allocation widely used in the existing literatures.

Image hiding has received significant attention due to the need of enhanced multimedia services such as multimedia security and meta-information embedding for multimedia augmentation. Recently, deep learning-based methods have been introduced that are capable of significantly increasing the hidden capacity and supporting full-size image hiding. However, these methods suffer from the necessity to balance the errors of the modified cover image and the recovered hidden image. In this paper, we propose a novel joint compressive autoencoder (J-CAE) framework to design an image hiding algorithm that achieves full-size image hidden capacity with small reconstruction errors of the hidden image. More importantly, our approach addresses the trade-off problem of previous deep learning-based methods by mapping the image representations in the latent spaces of the joint CAE models. Thus, both visual quality of the container image and recovery quality of the hidden image can be simultaneously improved. Extensive experimental results demonstrate that our proposed method outperforms several state-of-the-art deep learning-based image hiding techniques in terms of imperceptibility and recovery quality of the hidden images while maintaining full-size image hidden capacity.