The integration of space, air, and ground segments into unified Space-Air-Ground Integrated Networks (SAGINs) enables low-latency, ubiquitous, and scalable computing. However, such systems face critical challenges: ground terminals suffer from weak satellite links, UAV-based edge nodes have limited resources, and highly dynamic environments make it difficult to make efficient offloading and resource allocation decisions. Prior approaches often optimize either communication or computation in isolation and lack adaptability to real-time environmental feedback. This paper presents a novel perception-aware hybrid-action deep reinforcement learning (DRL) framework for joint optimization of task offloading, beamforming, and resource allocation in SAGINs. To improve tractability, the original non-convex problem is first decomposed using Block Coordinate Descent (BCD) and approximated with Successive Convex Approximation (SCA), generating a structured feasible action space. A Soft Actor-Critic (SAC) agent then learns policies over this space, informed by real-time UAV perception via mmWave radar and vision sensors that detect user density, link quality, and environmental blockages. The DRL agent operates over a hybrid action space, combining discrete offloading decisions with continuous controls such as beamforming weights, CPU frequency, and transmission power. We employ a constraint-aware action masking mechanism that prunes infeasible hybrid actions violating delay, power, or SNR limits, thereby accelerating learning while respecting SAGIN-specific constraints. Extensive simulations show that the proposed framework significantly outperforms greedy, no-perception DRL, and state-of-the-art DRL offloading algorithms in reducing latency and energy consumption, while improving offloading success and resource stability. These results highlight the effectiveness of combining analytical optimization structure with adaptive perception-driven learning for robust and scalable control in future SAGINs.

Facial expression and multi-feature manipulation play a vital role in applications such as media entertainment and biometric forensics. However, existing approaches face significant challenges, including semantic inconsistency, sensitivity to pose and illumination variations, and high computational demands. To address these challenges, this study proposes an improved latent diffusion-based deep generative adversarial network (IC-DGAN) framework that integrates multiple generators and discriminators, K-means clustering, and constructive pre-training to achieve precise semantic multi-feature and facial expression manipulation. The framework leverages scale-invariant feature transform (SIFT) and latent diffusion models to autonomously disentangle and manipulate facial attributes, enabling synchronized decomposition across multiple levels and generating high-resolution, realistic portraits. By mapping facial portraits back to the latent space, IC-DGAN enables robust attribute editing-including age, gender, and expression-while minimizing visual distortions. Comprehensive evaluations on benchmark datasets, including CelebA-HQ, CAS-PEAL, and RafD, demonstrate that IC-DGAN outperforms state-of-the-art methods, reducing unintended portrait variations by 12.3 %, enhancing manipulation accuracy by 8.7 %, and achieving a Fréchet Inception Distance (FID) of 25.94-significantly surpassing existing benchmarks. These results underscore the framework's potential for advancing high-fidelity facial editing, offering a robust solution to longstanding challenges.

In recent years, the manipulation and decomposition of facial expressions and features have gained significant attention due to their extensive applications in diverse fields, including media entertainment and biometric forensics. However, leveraging these frameworks for photo enhancement encounters substantial challenges, primarily due to the adaptive nature of facial features, which are highly susceptible to alterations in illumination, pose variations, and other factors significantly affecting their appearance. This study proposes an improved clustered-based deep generative adversarial network (IC-DGAN) framework featuring parallel generators and discriminators with loss functions for semantic expression and facial feature manipulation. The key concept involves guiding the deep generative framework through clustering and semantic feature prediction, facilitating synchronized decomposition across multiple levels, and generating diverse facial images. Our framework fuses the scale-invariant feature transform (SIFT) and the K-means cluster to autonomously partition semantic features and facial expressions into distinct dimensions. Combining clustering and latent space optimization aids our framework in generating more realistic results at specific abstraction levels. Additionally, for facial feature manipulation, our framework involves pretraining the feature prediction model by reversing the synthesized facial images to the IC-DGAN latent space. Through comprehensive experiments across various extensive datasets, we evaluated the efficacy of our framework against baseline methods. Our findings demonstrate that our framework efficiently mitigates unexpected portrait diversities and expression impacts compared to baseline approaches, leading to improved manipulations and reduced distortions.

Recently, deep learning has emerged as a promising approach for solving challenging resource distribution (RD) problems in vehicle-to-everything (V2X) wireless networks. How-ever, existing neural network architectures lack scalability, in-terpretability, and generalization. To address these limitations, in this study, we propose a new flexible graph neural network (FGNN)-based resource distribution framework for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) user selection and power management in V2X networks with several next- generation access points (APs) and a cluster of V2V and V2I communication users. In the proposed framework, we formu-lated an optimization problem with each V2V and V2I user with the least power constraint that adapts to V2X wireless network settings through training inactive users. Likewise, we consider the situation when every V2I user shares the band with a different group of V2V users. Moreover, we introduce a parameterization of the RD framework strategy employing a flexible graph neural network (FGNN) context derived from instantaneous channel conditions to learn the low-dimension features of every user/vehicle. To assess the execution of the framework, we conduct simulation experiments comparing it with baseline methods in terms of efficiency, sum rate, and fairness.

Due to the fast spread of data through digital media, individuals and societies must assess the reliability of information. Deepfakes are not a novel idea but they are now a widespread phenomenon. The impact of deepfakes and disinformation can range from infuriating individuals to affecting and misleading entire societies and even nations. There are several ways to detect and generate deepfakes online. By conducting a systematic literature analysis, in this study we explore automatic key detection and generation methods, frameworks, algorithms, and tools for identifying deepfakes (audio, images, and videos), and how these approaches can be employed within different situations to counter the spread of deepfakes and the generation of disinformation. Moreover, we explore state-of-the-art frameworks related to deepfakes to understand how emerging machine learning and deep learning approaches affect online disinformation. We also highlight practical challenges and trends in implementing policies to counter deepfakes. Finally, we provide policy recommendations based on analyzing how emerging artificial intelligence (AI) techniques can be employed to detect and generate deepfakes online. This study benefits the community and readers by providing a better understanding of recent developments in deepfake detection and generation frameworks. The study also sheds a light on the potential of AI in relation to deepfakes.

Cloud computing delivers a desirable environment for users to run their different kinds of applications in a cloud. Numerous of these applications (tasks), such as bioinformatics, astronomy, biodiversity, and image analysis, are deadline-sensitive. Such tasks must be properly allocate to virtual machines (VMs) to avoid deadline violations, and they should reduce their execution time and cost. Due to the contradictory environment, minimizing the application task's completion time and execution cost is extremely difficult. Thus, we propose a Cost-aware Quantum-inspired Genetic Algorithm (CQGA) to minimize the execution time and cost by meeting the deadline constraints. CQGA is motivated by quantum computing and genetic algorithm. It combines quantum operators (measure, interference, and rotation) with genetic operators (selection, crossover, and mutation). Quantum operators are used for better population diversity, quick convergence, time-saving, and robustness. Genetic operators help to produce new individuals, have good fitness values for individuals, and play a significant role in preserving the evolution quality of the population. In addition, CQGA used a quantum bit as a probabilistic representation because it has higher population diversity attributes than other representations. The simulation outcome exhibits that the proposed algorithm can obtain outstanding convergence performance and reduced maximum cost than benchmark algorithms.

In the past few years, the industry and academia have been working hard to establish and standardise vehicle-to-everything (V2X) communications, which is one of the vital emerging services for next generation wireless networks. Therewith, to control radio resource properly with balanced implementation complexity, a full-duplex V2V discovery mechanism in a 5G-V2X network based on a random backoff procedure is proposed to better utilize radio resources on which nearby vehicles establish their links. The main aims are to reduce complexity, latency, improve throughput and guarantee stability for V2V communication. The unemployed cellular network channel operates in full-duplex mode and leaves the channel as soon as they are informed that someone is in place through latency and throughput analysis technique. The channel sensing and identification are done in a cooperative manner before transmission. Furthermore, two effective resource distribution algorithms are proposed that grant the optimum resource distribution for V2V and V2I-Users. The detection and the throughput of full-duplex V2V communication in the proposed scheme have been formulated and the performance of the proposed scheme and validity of corresponding analysis are verified through simulation experiments.

The increase of mobile applications in the internet of vehicles (IoVs), necessitates the demand for higher computation capabilities. Vehicles can transfer related applications to another nodes for processing. In this paper, an efficient task offloading scheme for cellular vehicle to everything (C-V2X) is proposed to improve offloading reliability and latency. Vehicles are grouped into clusters, where vehicles in need of assistance can transfer their task to other vehicles for processing through the vehicle to vehicle (V2V) link, or transfer their task to the mobile edge computing (MEC) server via the vehicle to network (V2N) link. Matching theory is exploited for the task assignments. Simulation results reveals that the proposed scheme performs better than the existing schemes.

Over the past few years, industry and academia have worked hard to develop and standardize vehicle-to-everything (V2X) communication, which is one of the important emerging service for next-generation wireless networks (5G). Thereby, to manage radio resource efficiently with realistic execution complexity, a vehicle density based two-stage resource management scheme for 5G-V2X network is presented in this paper, whose key targets are to reduce latency, improve throughput and guarantee reliability for V2V-UEs and V2N-UEs. Particularly, during the first level, the resource distribution strategy depend on vehicles density information (VDI), that is different compared to channel state information (CSI) and queuing state information (QSI) used during the second level by considering buffer state information. Two efficient resource management algorithms are presented that grants the optimum resource distribution for V2N-UEs and V2V-UEs. Simulation experiments reveal the promising performance of proposed scheme compared with existing scheme.

In this paper, a clustering based resource management scheme for latency and sum rate optimization in V2X networks is proposed to identify distinguished demands for different kinds of vehicular links, namely cellular-vehicle-to-vehicle (C-V2V) links and cellular-vehicle-to-infrastructure (C-V2I) links, and to improve the performance of cellular user in terms of sum rate, latency and throughput for C-V2I links while guaranteeing reliability for every C-V2V connection. To address the fast channel changes due to high mobility, we present a clustering based resource management model to achieve band sharing and efficient power management that depends on large scale fading. Besides, we have also considered the resource management problem of cellular V2X and VANETs users to reduce data transmission impacts. Firstly, the total average sum rate of each C-V2I links is used as an optimization goal to increase the throughput and to reduce latency of the entire C-V2I link. Secondly, cluster based optimum algorithms are proposed which give the optimum resource management. Simulation results reveal that the proposed scheme outperforms the existing scheme.

Legacy TCP/IP protocol has gradually revealed many deficiencies, such as poor mobility and scalability. The distribution of information based on the content has a possible number of practical applications in the vehicular environment, such as congestion detection, collision avoidance, emergency announcements, parking notifications, and advertising. In this study, we have presented a technique for the distribution of information based on the content in a hybrid vehicle-to- everything (V2X) environment. The COC-V2X technique relies on contents that each vehicle having by communicating with each other, and has the potential to solve some of the problems that present in IP-based VANETs. It can also gain edge of both the cellular eNodeB if there exists the decentralized vehicle-to-vehicle communication technologies. We evaluate the performance of the proposed approach via realistic VANETs traces based scenarios. The preliminary conclusions illustrate that our proposed novel approach is superior to current legacy TCP/IP in terms of message delivery, low latency, and low overhead.

In vehicular ad hoc networks (VANETs), cellular vehicle-to-everything (C-V2X) is an emerging technology for communications between vehicle-to-infrastructure, vehicle-to-pedestrian, and vehicle-to-network which improves traffic efficiency, road safety, and the availability of infotainment services. Herein, a novel V2V-enabled resource allocation scheme based on C-V2X technology is proposed to improve the reliability and latency of VANETs. The key idea is that V2V communications based on cellular-V2X technology among vehicles remove the contention latency and can assist for longer distance communications. Particularly, we propose a hybrid architecture, where the V2V links are controlled by the cellular eNodeB in the overlay scheme. In this scheme, every vehicle periodically checks its packet lifetime and requests the cellular eNodeB to determine V2V links. The optimum resource allocation problem at the cellular eNodeB is to choose optimum receiver vehicles to determine V2V links and allocate suitable channels to minimize the total latency. This problem is equivalent to the maximum weighted independent set problem (MWIS-AW) with associated weights, which is NP-hard. In order to compute the weights, an analytical approach is developed to model the expected latency and packet delivery ratio. Moreover, a greedy cellular-based V2V link selection algorithm is proposed to solve MWIS-AW problem and develop a theoretical performance lower bound. Simulation results show that the proposed scheme significantly outperforms the existing schemes in terms of latency, throughput, and packet delivery ratio.

In vehicular ad hoc networks (VANETs), communication links break more frequently due to the high-speed vehicles. In this paper, a novel cluster-based VANET oriented evolving graph (CVoEG) model is proposed by extending the existing VoEG model to improve the reliability of vehicular communications. Here, the link reliability is used as a criterion for cluster members (CMs) and cluster heads (CHs) selection. The proposed CVoEG model divides VANET nodes (vehicles) into an optimal number of clusters (ONC) by using Eigen gap heuristic. In a given cluster, a vehicle will be selected as a CH, if it has a maximum Eigen-centrality score. Based on the CVoEG model, a reliable routing scheme called CEG-RAODV is proposed to find the most reliable journey (MRJ) from source to destination. Our simulation results show that the proposed scheme significantly outperforms the existing schemes in terms of reliability, reliable routing request (RRR), packet delivery ratio (PDR), end to end (E2E) delay, and throughput.