Label flipping attacks stand as a potent and practical threat to the integrity of machine learning models. While extensive research has focused on designing sophisticated attack and defense mechanisms, the underlying factors that govern a model's susceptibility remain underexplored. This paper reveals a critical phenomenon: the impact of label flipping attacks is highly differential across classes, strongly correlated with the intrinsic confusability between the source and target classes. We provide a rigorous theoretical analysis, demonstrating that a lower standardized separation between classes fundamentally leads to greater vulnerability. Grounded in this insight, we propose Confusability-Aware Contrastive Learning (CACL), a targeted defense that maximizes the feature-space separation for the most vulnerable class pairs. Extensive experiments validate the strong link between class separability and vulnerability, and show that CACL significantly mitigates the attack's impact while providing superior protection for the most susceptible classes. Our code is available at https://github.com/Pinlong-Zhao/Unequal-Vulnerability.

Integrated Sensing and Communication (ISAC) systems are playing an increasingly crucial role in modern wireless networks. However, in the ISAC scenario, the high transmission power required for communicating and sensing signals poses an increased risk of signal interception by eavesdroppers. To address this issue and enhance the physical layer security (PLS) of ISAC, we utilize Reconfigurable Intelligent Surfaces (RIS) to optimize the secrecy rate in the ISAC context, improving link security and effectively preventing eavesdropping. In the ISAC scenario, the location of the eavesdropper can be obtained through sensing. Leveraging this advantage, we employ Graph Neural Networks (GNN) to aggregate the node information of users and eavesdroppers, which iteratively passes messages and updates node states, thereby adaptively optimizing the transmitting beamforming vector and the RIS phase shift matrix. Simulation results show that this method is superior to the benchmark algorithm.

Graph Neural Networks (GNNs) have demonstrated remarkable capabilities in handling graph data. Typically, GNNs recursively aggregate node information, including node features and local topological information, through a message-passing scheme. However, most existing GNNs are highly sensitive to neighborhood aggregation, and irrelevant information in the graph topology can lead to inefficient or even invalid node embeddings. To overcome these challenges, we propose a novel Space Gravity-based Graph Neural Network (Gravity-GNN) guided by Deep Reinforcement Learning (DRL). In particular, we introduce a novel similarity measure called ''node gravity'', inspired by the gravitational force between particles in space, to compare nodes within graph data. Furthermore, we employ DRL technology to learn and select the most suitable number of adjacent nodes for each node. Our experimental results on various real-world datasets demonstrate that Gravity-GNN outperforms state-of-the-art methods regarding node classification accuracy, while exhibiting greater robustness against disturbances.

Deep neural networks (DNNs) have driven breakthroughs in autonomous driving through end-to-end methods, utilizing their powerful learning capabilities to generate vehicle controls directly from sensor data. However, maximizing the satisfaction of DNN inference requirements under the constraints of limited computing and energy resources on the vehicle side has emerged as a critical challenge in Vehicular Edge Computing(VEC). To address these challenges, we propose the reinforcement learning-empowered task diversion scheduling algorithm named RTD. This algorithm intelligently offloads computationally intensive portions of the DNN to Roadside Units (RSUs) by taking into account factors such as the battery coefficient and the type of DNNs. Firstly, we utilize the FLOPs method to model the data flow structure and computational load distribution of the DNNs. Subsequently, we formulate the task offloading model as an optimization problem that jointly considers latency, energy consumption, and the remaining battery power of the vehicle. Finally, after simplifying the optimization problem using the diversion algorithm, we employ the SAC method to determine the optimal offloading strategy. Extensive experiments demonstrate that RTD significantly reduces overall task completion time, effectively handles time-sensitive tasks, properly protects low-battery vehicles, and adapts well to dynamic network environments.

Graph federated learning (GFL) is increasingly utilized in domains such as social network analysis and recommendation systems, where non-IID data exist extensively and necessitate a strong emphasis on personalized learning. However, existing methods focus only on the personality among different clients instead of the personality within a client which widely exists in the real social networks, where intra-client personality addresses the heterogeneity of known data, while inter-client personality always tackle client heterogeneity under privacy constraint. In this paper, we propose a novel automatic personalized graph federated learning (PGFL) scheme named FedCCH to capture both inter-client and intra-client heterogeneity. For intra-client heterogeneity, we innovatively propose the learnable Personalized Factor (PF) to automatically normalize each graph representation within clients by learnable parameters, which weakens the impact of non-IID data distribution. For inter-client heterogeneity, we propose a novel hash-based similarity clustering method to generate the hash signature for each client, and then group similar clients for joint training among different clients. Ultimately, we collaboratively train intra-client and inter-client modules to improve the effectiveness of capturing the heterogeneity of the graph data of clients. Experiment results demonstrate that FedCCH outperforms other state-of-the-art baseline methods.

Role discovery assist in various applications of online social networks, such as water army detection, shopping recommendation, rumor tracing, etc. However, existing studies often overlook the significance of hierarchical structures in online social networks, which are crucial for understanding the roles played by different users. To address this gap, we propose a novel approach based on hyperbolic graph learning, called HyperRole, which effectively leverages the hierarchical structure of online social networks for role discovery. HyperRole first extracts structural features from users and constructs user sequences based on feature similarity, capturing the relationships between users across different scales. Then, we learn role information from structural features by hyperbolic graph Transformer to embed users into the hyperbolic space, preserving the hierarchical structure between users and enabling interactions between users of the same level that are far away from each other. Additionally, we leverage the hierarchical distance between the target user and other users within the same sequence to guide and modify the role information of the target user. Based on the generated user role embeddings, we train a multi-class classifier to classify roles. Extensive experiments on several real-world network datasets demonstrate that our model outperforms existing baseline methods, showcasing its superior performance.

Core enterprises can provide effective assistance for financing small and medium-sized enterprises (SMEs). Promoting data sharing between both parties is of great significance. However, a real issue is that core enterprises may not be willing to share information for SMEs or financial institutions due to concerns about privacy leakage. Vertical federated technology (VFT) considers the privacy protection issues of distributed data and has become an advanced technology for solving distributed data cooperation. But its execution is also influenced by various factors. This article conducts a dynamic evolutionary game analysis of cooperation based on the new technology. A three-party evolutionary game model was constructed. It highlights the influencing factors of the application of VFT in the cooperation for financing of SMEs. The findings indicate that VFT technology can be considered an effective strategy for solving the financing problem of SMEs under specific conditions.

Joint Vehicle-to-vehicle (V2V) and Vehicle-to-Infrastructure (V2I) offloading presents an efficient approach to leverage surplus computing resources from neighboring devices, thereby expanding the coverage of computing resources supply in the context of the Internet of Vehicles. However, many studies overlook the significance of topological communications caused by the rapid movement of vehicles, privacy, and communication intentions. To achieve efficient task offloading when facing various topological link structures, we first propose a novel topological link-aware task co-offloading (TLCO) method designed for partially offloading in the joint V2V and V2I system. Next, we model the sequential subtasks offloading process as the Markov Decision Process (MDP) and utilize the Double Deep Q-Network (DDQN) algorithm to optimize the total delay of the proposed system. Additionally, we put forth a prediction framework named Sliding Time Windows and TLCO algorithm (STW-TLCO) to accurately forecast the computation load at various time windows using pulsed parameters. Extensive experimental results demonstrate the effectiveness and superiority of the proposed TLCO-DDQN algorithm in comparison to other Deep Reiforcement Learning (DRL)-based and Greedy-based approaches. Furthermore, the STW-TLCO algorithm exhibits high accuracy, with an R-squared value exceeding 96%, confirming its predictive capabilities.

The unique capabilities of Unmanned Aerial Vehicles (UAVs), including their superior mobility, flexibility, and line-of-sight transmission, have made them well-suited for facilitating Aerial Edge Computing (AEC). This computing paradigm is particularly beneficial for meeting the computing demands of User Equipments (UEs) in emergency situations, as it offers efficient support for task offloading. Considering the service requirements of UEs, it is essential to minimize the processing delay experienced by UEs in AEC systems. This is accomplished through the joint optimization of the UAV trajectory, flight speed, and task offloading ratio allocation for UEs. Due to the non-convex nature and the continuous action space of the problem, recent studies have turned to the Deep Deterministic Policy Gradient (DDPG) to tackle similar challenges. However, Deep Neural Networks (DNNs) employed in DDPG are limited to extracting latent information solely from Euclidean data, and are similarly constrained by the highly dynamic changes in channel states within AEC networks, thereby disregarding the valuable features inherent in the structural information. In order to alleviate the task offloading problem in AEC systems, we propose a novel Graph Convolutional Pooling-DDPG (GCP-DDPG) algorithm by exploiting the graph-based multi-relational derivation capability of the multi-Relational Graph Convolutional Network (R-GCN) and employing the reinforcement learning technique. Extensive simulation experiments are conducted to evaluate the superiority and effectiveness of the GCP-DDPG algorithm. The results demonstrate a remarkable performance improvement of 34.6% compared to state-of-the-art approaches.

The task of network alignment aims to identify corresponding nodes across multiple networks, with applications in various fields such as social network analysis and bioinformatics. Traditional methods typically focus on the topological structure of networks at a specific level, but they may overlook important properties exhibited by many networks, such as scale-free properties and specific power-law structures often found in social networks. Consequently, these methods fail to effectively capture and utilize such information, leading to misalignment. In this article, we propose a network alignment framework that incorporates both topological and attribute information from multiple levels in the network, including homogeneity, power-law, and higher order structures. We introduce a Euclidean hyperbolic interactive graph learning method specifically designed for modeling power-law structures in networks, aiming to improve the accuracy of network alignment. To evaluate the effectiveness of our proposed method, we conduct experiments on several real-world datasets. The results demonstrate that our approach achieves higher accuracy compared to other advanced baselines.

Reconfigurable intelligent Surfaces (RIS) and half-duplex decoded and forwarded (DF) relays can collaborate to optimize wireless signal propagation in communication systems. Users typically have different rate demands and are clustered into groups in practice based on their requirements, where the former results in the trade-off between maximizing the rate and satisfying fine-grained rate demands, while the latter causes a trade-off between inter-group competition and intra-group cooperation when maximizing the sum rate. However, traditional approaches often overlook the joint optimization encompassing both of these trade-offs, disregarding potential optimal solutions and leaving some users even consistently at low date rates. To address this issue, we propose a novel joint optimization model for a RIS- and DF-assisted multiple-input single-output (MISO) system where a base station (BS) is with multiple antennas transmits data by multiple RISs and DF relays to serve grouped users with fine-grained rate demands. We design a new loss function to not only optimize the sum rate of all groups but also adjust the satisfaction ratio of fine-grained rate demands by modifying the penalty parameter. We further propose a two-phase graph neural network (GNN) based approach that inputs channel state information (CSI) to simultaneously and autonomously learn efficient phase shifts, beamforming, and relay selection. The experimental results demonstrate that the proposed method significantly improves system performance.

Federated Learning (FL) empowers multiple clients to collaboratively learn a global generalization model without the need to share their local data, thus reducing privacy risks and expanding the scope of AI applications. However, current works focus less on data in a highly nonidentically distributed manner such as graph data which are common in reality, and ignore the problem of model personalization between clients for graph data training in federated learning. In this paper, we propose a novel personality graph federated learning framework based on variational graph autoencoders that incorporates model contrastive learning and local fine-tuning to achieve personalized federated training on graph data for each client, which is called FedVGAE. Then we introduce an encoder-sharing strategy to the proposed framework that shares the parameters of the encoder layer to further improve personality performance. The node classification and link prediction experiments demonstrate that our method achieves better performance than other federated learning methods on most graph datasets in the non-iid setting. Finally, we conduct ablation experiments, the result demonstrates the effectiveness of our proposed method.

Due to numerous computation-intensive and delay-sensitive tasks in the Internet of Vehicles (IoV), Vehicular Edge Computing (VEC) is increasingly playing a crucial role as a key solution in the IoV. However, how to concurrently enhance communication quality and reduce the cost of latency and energy has emerged as a critical challenge in VEC. To tackle the above problem, we propose a Lyapunov-guided offloading based on the Soft Actor-Critic (SAC) algorithm, named LySAC, to minimize the average cost of the Integrated Sensing and Communications (ISAC) technology-aided IoV, where ISAC technology can effectively improve the communication quality by harnessing high-frequency waveforms to seamlessly integrate communication and sensing functionalities. First, we model the offloading process of ISAC-Aided IoV as an optimization problem of the joint cost of delay and energy with long-term energy consumption and queue stability. Then we formulate the optimization problem as a Lyapunov optimization and utilize the SAC method to find the optimal offloading decisions. Finally, we conduct extensive experiments and the results demonstrate the effectiveness and superiority of the proposed LySAC in minimizing total cost while maintaining queue stability and meeting long-term energy requirements compared with other several baseline schemes.

With the increasingly humanized and intelligent operation of Industrial Internet of Things (IIoT) systems in Industry 5.0, delay-sensitive and compute-intensive (DSCI) devices have proliferated, and their demand for low latency and low power consumption has become more and more eager. In order to extend the battery life and improve the quality of user experience, we can offload DSCI-type workloads to mobile edge computing (MEC) servers for processing. However, offloading massive amounts of tasks will incur higher energy consumption, which is a severe test for the limited battery capacity of devices. In addition, the delay caused by frequent communication between IIoT devices and MEC cannot be ignored. In this article, we first formulate the stochastic computation offloading problem to minimize long-term energy consumption. Then, we construct a virtual queue using perturbed Lyapunov optimization techniques to transform the problem of guaranteeing task deadlines into a stable control problem for the virtual queue. Based on this, a novel delay-aware energy-efficient (DAEE) online offloading algorithm is proposed, which can adaptively offload more tasks when the network quality is good. Meanwhile, it delays transmission in the case of poor connectivity but ensures that the deadline is not violated. Moreover, we theoretically demonstrated that DAEE can enable the system to achieve an energy-delay tradeoff, and analyzed the feasibility of constructing virtual queues to assist the actual queue offloading tasks. Finally, simulation results show that DAEE performs well in minimizing energy consumption and maintaining low latency, especially for DSCI-type tasks.

The rapid development of Vehicular Edge Computing (VEC) provides great support for Collaborative Vehicle Infrastructure System (CVIS) and promotes the safety of autonomous driving. In CVIS, crowd-sensing data will be uploaded to the VEC server to fuse the data and generate tasks. However, when there are too many vehicles, it brings huge challenges for VEC to make proper decisions according to the information from vehicles and roadside infrastructure. In this paper, a reverse offloading framework is constructed, which comprehensively considers the relationship balance between task completion delay and the energy consumption of User Vehicle (UV). Furthermore, in order to minimize the overall system consumption, we establish an adaptive optimal reverse offloading strategy based on Deep Q-Network (DQN). Simulation results demonstrate that the proposed algorithm can effectively reduce the energy consumption and task delay, when compared with the full local and fixed offloading schemes.

With the rapid development of Artificial Intelligence (AI) and Internet of Things (IoT), we have to perform increasingly more resource-hungry and compute-intensive applications on IoT devices, where the available computing resources are insufficient. With the assistance of Mobile Edge Computing (MEC), offloading partial complex tasks from mobile devices to edge servers can achieve faster response time and lower energy consumption. However, it still suffers from finding the optimal offloading decision when the total amount of computations overflows the available computing resources in MEC systems. In this paper, we establish a multi-user and multi-task MEC model and design an offloading indicator, through which we analyze what the current environment belongs to. In the cases where the computational resources of devices are sufficient or partially sufficient, we utilize the relationship between the offloading indicator and the cost incurred by the tasks that are executed in the current workflow to find the optimal offloading decision. In the cases where the computation on local and edge are both insufficient, we propose a novel Offloading Algorithm based on K-means clustering and Genetic algorithm for solving Multiple knapsack problem (OAKGM), aiming not only to jointly optimize the time and energy incurred by the tasks that are executed in the current workflow, but also to penalize the overflowed computations so that the task pressure in the next workflow can be greatly reduced. In addition, a simplified Offloading Algorithm based on Multiple Knapsack Problem (OAMKP) is proposed to further cope with the environments with a large number of users or tasks. Experimental results demonstrate the effectiveness and superiority of the proposed algorithms when compared with several benchmark offloading algorithms, which can better exploit the computing capacities of IoT devices and the edge server, greatly avoid resource occupation in edge nodes and make sustainable MEC possible.

To evaluate key clients comprehensively and objectively, a general comprehensive evaluation system of key clients is defined based on the analysis of the third party logistics enterprises. Then a formalized expression and basic element model of key client comprehensive evaluation problem is given. Furthermore, a key client comprehensive evaluation approach based on extension theory is presented. It adopts the optimal degree evaluation approach from the extension theory, which extends cantor set theory and fuzzy set theory in the semantics. The extension theory based comprehensive evaluation approach consists of three main steps. Firstly we need to determine the measuring weights using the AHP method; Secondly, we need to establish the dependent function, and calculate the qualification degree of each client using this formula, also we should normalize it. Thirdly, we calculate the optimal degree to evaluate the clients. The client with the highest optimal degree is the most important client for enterprise. This approach is implemented as computer program and integrated into the third party logistics intelligent information platform. Results show that the key client comprehensive evaluation approach is effective and efficient.