The rapid iteration of artificial intelligence (AI) and 5G technologies has created essential foundations for Metaverse, easing bottlenecks in content generation, real-time interaction, and large-scale deployment. Integrating unmanned aerial vehicle (UAV) with semantic communication (SemCom) further provides a lightweight sensing and uplink solution, but semantic compression and bias may degrade fidelity. Generative AI (GAI), with powerful contextual modeling and generation capabilities, helps mitigate these issues. Based on this, this paper proposes a GAI-aided SemCom architecture and evaluates the feasibility of applying it to low-altitude internet of things (IoT) networks. We build evaluation models for representative image compression and GAI-aided SemCom techniques, replacing traditional task assumptions with realistic cases. Then, taking UAV networks as an example, we design a path planning and two task allocation schemes. Specifically, the UAV path planning strategy together with a greedy task allocation scheme improves the Metaverse update frequency and ensures the data freshness, while a parametrized deep Q-network (PDQN) task allocation scheme jointly optimizes Metaverse fidelity and freshness through mixed action selection, i.e., preprocessing methods (discrete) and compression size (continuous). Extensive analysis and numerical results corroborate that GAI-aided SemCom technology has practical significance in low-altitude IoT networks. Through the collaboration of multiple data processing schemes and the rational resource allocation, the fidelity and freshness of Metaverse can be greatly improved.

Reversible data hiding in JPEG images is critical for secure multimedia applications, while, existing histogram modification schemes are confined to fixed 1D or 2D dimensions. These methods fail to adapt to the characteristics of cover images and the demands of embedded data, resulting in suboptimal trade-offs among embedding capacity, image quality, and file size. To address these issues, this study proposes a Multi-Dimensional Histogram Modification Framework that advances histograms from "fixed dimension" to "variable dimension" and extends them to high-dimensional structures. Our key contributions are as follows: first, we propose an adaptive dimension selection strategy that dynamically determines the optimal histogram dimension by evaluating the capacity and distortion for each cover image and embedding task; second, we develop a high-dimensional histogram construction method that combines AC coefficients with absolute values of 1 and 2 at the same frequency to enhance the utilization of coefficient correlation; third, we design an optimized mapping algorithm that searches for the optimal mapping matrix to minimize both distortion and file expansion. Experimental results show that the proposed method outperforms existing 1D and 2D histogram modification schemes. On average, it increases the embedding capacity by 5000 bits, improves the image quality by 0.2 dB, and reduces the file size by 4000 bits.

Backdoor attacks pose significant security threats to deep neural networks. A backdoored model performs well on benign samples, but if the hidden backdoor is activated by a trigger defined by the attacker, the model's predictions will be maliciously altered. Existing backdoor attacks typically adopt a trigger-agnostic setup, where different poisoned samples in the backdoor attack methods contain the same trigger, which is usually visible or fragile. To address these limitations, we propose a sample-specific, sample-edge-adaptive backdoor attack method. Specifically, we utilize edge detection algorithms to identify edge structures in images as the target poisoning region, embedding the edge information into the least significant bits of the image using a steganographic method. This generates a sample-specific trigger pattern. Since image structure retains its semantic meaning during data transformation, this trigger pattern exhibits inherent robustness to data conversion. Our proposed attack is extensively evaluated across various network models and datasets, demonstrating its generalizability, superior stealthiness, better robustness compared to existing backdoor attack methods, and strong resistance against state-of-the-art defense techniques while maintaining high benign accuracy.

Reversible data hiding in encrypted JPEG images (JPEG-RDH-EI) is one of the key technologies for securely storing and managing confidential images in cloud environments. However, existing methods typically operate only in the coefficient domain or the encoding domain, failing to fully exploit the characteristics of encrypted images, which results in limited embedding capacity and significant file expansion. To address these limitations, this paper proposes a high-capacity JPEG-RDH-EI scheme based on multi-domain embedding. To reduce file expansion, a rotation model is devised that leverages the correlation of DCT coefficients within a range that does not notably alter the run length. This model embeds secret data by strategically rotating and rearranging these DCT coefficients. On this basis, the scheme constructs an optimal VLC mapping relationship and adaptively adjusts embedding parameters according to the characteristics of the encrypted image, based on the RSV histogram shifting technique, achieving data embedding in the encoding domain, thereby further enhancing embedding capacity. The proposed scheme supports fully separable data extraction and image recovery, making it suitable for various application scenarios. Evaluation results demonstrate that the maximum embedding capacity of this scheme is 2 to 3 times greater than that of existing advanced schemes, with some images achieving a maximum embedding capacity of over 100,000 bits. Moreover, the proposed scheme achieves an average unit file expansion of only about 0.03, outperforming current advanced methods.

Reversible Adversarial Examples (RAE) are designed to protect the intellectual property of datasets. Such examples can function as imperceptible adversarial examples to erode the model performance of unauthorized users while allowing authorized users to remove the adversarial perturbations and recover the original samples for normal model training. With the rise of Self-Supervised Learning (SSL), an increasing number of unlabeled datasets and pre-trained encoders are available in the community. However, existing RAE methods not only rely on well-labeled datasets for training Supervised Learning (SL) models but also exhibit poor adversarial transferability when attacking SSL pre-trained encoders. To address these challenges, we propose RAEncoder, the first framework for RAEs without the need for labeled samples. RAEncoder aims to generate universal adversarial perturbations by targeting SSL pretrained encoders. Unlike traditional RAE approaches, the pre-trained encoder outputs the feature distribution of the protected dataset rather than classification labels, enhancing both the attack success rate and transferability of RAEs. Extensive experiments are conducted on six pre-trained encoders and four SL models, covering aspects such as imperceptibility and transferability. Our results demonstrate that RAEncoder effectively protects unlabeled datasets from malicious infringements. Additional robustness experiments further confirm the security of RAEncoder in practical application scenarios.

Diffusion models have garnered significant attention in deep generative modeling due to their exceptional ability to generate diverse and high-quality samples across various data modalities. However, their security vulnerabilities, particularly backdoor attacks, remain largely unexplored, resulting in unpredictable and potentially malicious image generation. This paper introduces SBADiffusion, an invisible backdoor attack method that integrates steganography and quantization techniques to embed undetectable triggers into diffusion models. Specifically, steganography generates triggers by embedding subtle noise patterns into images, enabling these triggers to carry secret information without being perceptible to the human eye. Quantization technique further enhances the stealth of the triggers by optimizing their embedding to minimize visible artifacts or irregularities. Through a meticulously designed framework, this method achieves a delicate balance between visual stealth and attack reliability. Experimental results demonstrate that even at a low poisoning rate of 10 %, the attack success rate exceeds 90 %, and the mean squared error (MSE) of the poisoned images is significantly lower than that of existing methods. These findings not only highlight the stealth and precision of the proposed method but also reveal its potential for malicious exploitation, underscoring the urgent need to develop robust defense mechanisms against such threats in diffusion models.

As a critical element in intelligent transportation systems (ITS), roadside units (RSUs) are pivotal in delivering superior Internet of Vehicles (IoV) services encompassing intelligent traffic management, accident prevention, and emergency rescue. Considering the high deployment and maintenance costs of RSUs, many studies focus on the efficient RSU deployment issues. However, due to the high visibility of the ITS system, RSUs are highly susceptible to external attacks, which is commonly overlooked in existing RSU deployment researches. Specifically, the Sybil attack is one of the most dangerous attacks against ITS, it can reshape the network state by forging multiple identities, interfering with the operator’s reputation assessment or causing severe DDoS. Therefore, we propose a joint heuristic scheme that combines the advantages of particle swarm optimization and double local-search memetic algorithm to solve the city RSU deployment problem in Sybil attack environments. It can find solutions with higher fitness values and guarantees that the IoV has the capability to detect Sybil attacks. Numerical results show that our proposed scheme not only outperforms other traditional solutions regarding signal validity coverage, overlap rate, and initial propagation speed of accident information, but also performs satisfactorily in Sybil attack detection.

Abstract Metaheuristic is one of the techniques to improve the security of image encryption. However, existing metaheuristic image cryptosystems based on metaheuristic may have convergence difficulties during the optimization process, which cause insecurity and slow convergence. Besides, the time cost of the parallel execution model applied to metaheuristic image cryptosystems is not low enough. Therefore, a parallel many‐objective optimized key generation framework is proposed. Firstly, if four or more security indicators of cryptosystem, which are the results of security test, need to be optimized, the many‐objective optimization algorithm is employed to the proposed framework. With method adjusts the chaotic system parameters as the optimization key, which effectively avoid the convergence difficulty of the encryption key. Secondly, a master‐slave parallel model is improved to metaheuristic encryption. The model allocates the most time‐consuming fitness calculation work to slave nodes, which makes the modified model more reasonable and thus reduces the encryption time. To evaluate the performance of the proposed framework, a specific encryption scheme is constructed, that utilizes a 2D quadric map and many‐objective optimization algorithm based on dominance and decomposition (MOEA/DD) to optimize five security indicators. Experimental results reveal that this scheme has good security performances and less parallel encryption time.

Reversible adversarial example (RAE) is an effective cutting‐edge technology for protecting the intellectual property (IP) of datasets. However, existing RAE schemes primarily focus on the adversarial and restoration capabilities of adversarial examples (AE), with little attention paid to traceability, which is crucial for IP protection. This oversight leads to the inability to prevent authorized users from redistributing data, thereby posing significant IP security risks. To address this issue, we propose a novel approach named TAE‐RWP, wherein adversarial perturbations in AEs are treated as tools for IP verification. To enable the traceability of AEs, we introduce varying degrees of warping to the adversarial perturbations within the AEs of authorized users, utilizing the warping degree as a traceable feature. To further strengthen traceability, we adopt a technique named “random warping” to maintain the resilience of adversarial perturbations against distortions, and employ a strategy named “noise mode” to improve the verification model’s capacity to recognize distortion features. Experimental results indicate that AEs generated by TAE‐RWP exhibit remarkable adversarial strength and restoration abilities, while the verification model demonstrates excellence in recognizing distortion features.

Pairwise modification is one of the most effective ways to solve the critical issues of balancing the embedding capacity, image distortion, and file expansion in JPEG reversible data hiding (RDH). To design a satisfactory scheme based on pairwise modification, existing schemes focus on improving pairing rules, two-dimensional (2D) mappings, or ordering strategies separately while neglecting the connections between them. As a result, once pairing rules are changed, the correlative 2D mapping and ordering strategies are no longer available. To address such issues, this study proposes a framework that automatically generates optimal 2D mappings and efficient ordering strategies only by carefully initializing pairing rules. To construct optimal 2D mappings, a 2D mapping mathematical model is built to form a feasible 2D mapping solution space, in which optimal solutions are found, to assign efficient mappings for pairs with high probability. To design efficient ordering strategies, all frequencies are ranked according to an embedding evaluation model to determine more suitable ACs for data embedding. To initialize better pairing rules, this study selects nonzero ACs within ±2 for interblock pairing to form a more centralized pairwise histogram. The experimental results show that the proposed scheme introduces minor file expansion and obtains better visual quality than existing JPEG RDH schemes when the payload is the same as.

Mobile edge computing (MEC) has emerged as a promising approach to address the time-sensitive requirements of mobile Internet of Vehicles (IoVs) systems. Unfortunately, the current deployment density of roadside units (RSUs) is relatively sparse, and the direct V2I communication coverage is limited, making it impossible to meet the communication and computing requirements of all vehicles. There is an urgent need for V2V communication to assist V2I communication, which can achieve a wider coverage of RSUs, a diversified selection of task processing locations, and even load balancing between RSUs. However, V2V communication also faces a series of challenges. On the one hand, due to the sparsity, time-varying, and high-speed mobility of vehicle nodes in IoVs, the selection of collaborative communication paths becomes more difficult. On the other hand, there are inevitably malicious vehicles in IoVs, and how to achieve efficient task processing while ensuring privacy and driving safety is also a problem worth studying. Existing research generally optimized the delay of direct V2I task offloading, ignoring the necessity of V2V-assisted communication and the presence of malicious communication nodes. To address the above challenges, we present a vehicular edge computing network structure with multiple communication modes, including V2V, V2I, etc, and use a recommended trust model to analyze the trust degree between the nodes in IoVs. Then, we discuss the issue of trusted task offloading for IoVs and propose a Deep Deterministic Policy Gradient (DDPG) scheme. The numerical results indicate that our proposed strategy outperforms current methods in terms of task offload latency and credibility.

The popularity of ChatGPT demonstrates the immense commercial value of natural language processing (NLP) technology. However, NLP models are vulnerable to piracy and redistribution, which harms the economic interests of model owners. Existing NLP model watermarking schemes struggle to balance robustness and covertness. Robust watermarking require embedding more information, which compromises their covertness; conversely, covert watermarking are challenging to embed more information, which affects their robustness. This paper proposes an NLP model watermarking framework that uses multi-task learning to address the conflict between robustness and covertness in existing schemes. Specifically, a covert trigger set is established to implement remote verification of the watermark model, and a covert auxiliary network is designed to enhance the watermark model's robustness. The proposed watermarking framework is evaluated on two benchmark datasets and three mainstream NLP models. The experiments validate the frame-work's excellent covertness, robustness, and low false positive rate.

To meet the future demands for ubiquitous communication coverage and temporary / unexpected computing resources, aerial computing networks have been envisioned as a new paradigm. Nevertheless, dynamic changes on the network make it particularly challenging to achieve global optimal resource allocation. As an emerging technology, digital twin (DT) can represent real objects in physical network by creating virtual models. With the help of DT, we can easily obtain comprehensive real-world high-fidelity state information for model training, so as to achieve intelligent efficient decision-making. Accordingly, DT-based aerial computing networks have emerged as a potential solution. Note that available researches mostly assumed simple ground user distribution like uniform distribution, and adopted binary / partial offloading in task processing, neglecting the task separability and data inter-dependency among subtasks. Toward this end, we introduce DT into aerial computing networks, and study the problem of intelligent UAV deployment and resource allocation. Specifically, we firstly propose a DT-assisted UAV deployment strategy and model the data inter-dependency among subtasks. After that, two DT-assisted hybrid (binary and partial) task offloading schemes are presented, i.e., heuristic greedy and DQN-based schemes. Extensive analysis and numerical results confirm the effectiveness of our proposed DT-assisted UAV deployment and hybrid task offloading strategies.

Robust reversible watermarking (RRW) is one of the most popular areas in information hiding. Existing schemes have two drawbacks: 1) schemes that can resist conventional attacks often fail to resist geometric attacks, and 2) schemes that can resist geometric attacks often are not robust against conventional attacks and have poor stability. Inspired by the high robustness of fractional-order orthogonal moments (FoOM) and the good feature of resistance to geometric attacks of Zernike moments and pseudo-Zernike moments (ZM/PZM), in this research, FoOM is used to optimize ZM/PZM to obtain FoZM/FoPZM (namely, fractional-order Zernike moments and fractional-order pseudo-Zernike moments). Furthermore, a denoiser is proposed to preprocess the watermarks to improve the robustness against geometric and conventional attacks, the amount of extracted auxiliary information is decreases and the extraction process of auxiliary information is designed to be more stable. Specifically, first, the source of the difference between the watermarked image and the carrier image is identified, that difference is represented with less information, and then that information is embedded into the cover image as auxiliary information. Second, the watermark is embedded in the low-order FoZM/FoPZM component. Finally, the watermarked image is denoised using a denoiser before extracting the watermark. The experimental results show that the scheme has good stability and strong robustness. Compared with existing methods, the proposed scheme has a small and stable auxiliary information size, strong robustness to noise attacks such as Gaussian noise and salt-and-pepper noise attacks, and better resistance to geometric attacks such as rotation and scaling attacks.

With the gradual commercialization of 5G, especially the widespread application of artificial intelligence (AI) technology, the Internet of Things (IoT) continues to expand and has integrated into every aspect of our lives. While enjoying the convenience brought by IoT, we also face unprecedented challenges, including ubiquitous and unpredictable demands for communication and computing resources. In consideration of their flexible deployment, low cost, and easy expansion, UAV edge computing IoT networks (UECINs), which adopt unmanned aerial vehicles (UAVs) to provide fast communication and computing services, have emerged as a promising solution. Note that there have been a number of studies focusing on UAV’s position deployment and trajectory design, resource allocation in UECIN. However, most existing works proposed short-term service provisioning systems with a fixed number of UAVs, ignoring the problem of UAVs’ limited battery power and the possible changes of ground users’ number, locations, and resource requirements. To address these issues, we present a dynamic UECIN framework with autonomous prediction characteristics, aiming to stably provide mobile-edge computing services for ground users in a certain area over a long period of time. This framework can not only support UAV’s dynamic entry and exit according to the real-time needs of ground users but also update their position deployment based on the distribution of ground users. As we know, we are the first to propose UECIN with a dynamic entry and exit mechanism. Besides, an efficient and load-balancing task allocation scheme is further given, and extensive analysis and numerical results corroborate the feasibility and superior performance of our framework.

This article investigates an unmanned aerial vehicle (UAV)-assisted wireless-powered mobile-edge computing (MEC) system, where the UAV powers the mobile terminals by wireless power transfer (WPT) and provides computation service for them. We aim to maximize the computation bits of terminals while ensuring fairness among them. Considering the random trajectories of mobile terminals, we propose a soft actor–critic (SAC)-based UAV trajectory planning and resource allocation (SAC-TR) algorithm, which combines off-policy and maximum entropy reinforcement learning to improve the convergence of the algorithm. We design the reward as a heterogeneous function of computation bits, fairness, and destination. Simulation results show that SAC-TR can quickly adapt to varying network environments and outperform representative benchmarks in various situations.

Watermarking technology is commonly used to solve various problems in digital rights management and multimedia security. If a watermarking scheme with multiple purposes applies single method, it will easily cause the destruction of the hidden messages in particular attacks. For the copyright protection and tamper detection of color images, this research proposed a robust-fragile watermarking scheme. The two different embedding schemes embed the watermark into the R layer and G layer after NSST (nonsubsampled shearlet transform) and DWT (discrete wavelet transform) transformation. The hash sequence generated by the R layer and the G layer is served as fragile watermarks and is embedded into the B layer by the LSB (least significant bit) method. Finally, an improved rotation correction is applied to better extract the watermark under the rotation attack. Experimental results show that the proposed method is more accurate than the existing ones in terms of rotation angle correction and can effectively resist general attacks such as noise, filtering, and JEPG compression. Moreover, the proposed fragile watermark can locate the tamper position when malicious tamper occurs. Except cropping attack, the true-positive rate (TPR) reaches 1 for all attacks.

Delayed offloading is a widely accepted solution for mobile users to offload their traffic through Wi-Fi when they are moving in urban areas. However, delayed offloading enhances offloading efficiency at the expense of delay performance. Previous works mainly focus on the improvement of offloading efficiency while keeping delay performance in an acceptable region. In this paper, we study the impact of the user mobility on delayed data offloading in respect to the tradeoff between offloading efficiency and delay performance. We model a mobile terminal with delayed data offloading as an M/MMSP/1 queuing system with three service states. To be practical, we consider the feature of currently commercial mobile terminals in our analysis. Our analytical result shows that the mobility of the users can reduce the queueing delay incurred by the delayed offloading, and suggests that delayed offloading strategies can be optimized according to the mobility of the terminals once the delay requirement is given.

In this paper, we describe a cloud platform for health care tourism of Hainan province, China. The relevant business process is designed in a way that the characteristics of health care are taken into account. A scheme that combines medical tourism with a self-health care system and a nursing system is proposed. The data storage structure of the health care system is given, together with the specific storage way, which is based on the Azure platform.

This paper proposes a novel scheme for RFID anti-counterfeiting by applying bisectional multivariate quadratic equations (BMQE) system into an RF tag data encryption. In the key generation process, arbitrarily choose two matrix sets (denoted as A and B) and a base Rab such that [AB] = λRABT, and generate 2n BMQ polynomials (denoted as p) over finite field Fq. Therefore, (Fq, p) is taken as a public key and (A, B, λ) as a private key. In the encryption process, the EPC code is hashed into a message digest dm. Then dmis padded to d'mwhich is a non-zero 2n×2n matrix over Fq. With (A, B, λ) and d'm, Smis formed as an n-vector over F2. Unlike the existing anti-counterfeit scheme, the one we proposed is based on quantum cryptography, thus it is robust enough to resist the existing attacks and has high security.