The cell-free (CF) network architecture has promising applications in Internet of Things (IoT) networks due to its dynamic and adaptive nature in resource allocation. However, due to the openness of wireless channels and the information interaction of sensitive data, the security issues of CF IoT networks have become more severe, especially in the case of powerful opponents. In this article, a high-level secure transmission technique is utilized to protect the privacy of users, which is called covert communication. Specifically, in the CF IoT network conceived, one IoT device secretly transmits sensitive information to an access point (AP) under the cover of a selected jammer to avoid being detected by other curious IoT devices, which are regarded as potential eavesdroppers (Eves) and determined by the central processing unit (CPU) based on greedy degree. Then, we analyze the joint impact of jamming and greedy degree on the detection error probability (DEP) for Eve, and determine Eve’s minimum DEP as well as the corresponding optimal threshold. To enhance energy efficiency while ensuring communication security, three jamming scheduling schemes have been proposed, namely, the jamming scheduling for both the receiver (Bob) and Eve (JSBE), the jamming scheduling for Eve (JSE), and the jamming scheduling for Bob (JSB). Numerical results indicate that greedy degree dominates the average minimum DEP for Eve when IoT devices tend to be lightweight. Furthermore, JSBE scheme demonstrates superiority in terms of covert rate, covert outage probability (COP), and covert energy efficiency (CEE), which provides an effective solution for high-security transmission of energy-constrained nodes in CF IoT networks.

In this paper, a covert wireless-powered relay (CWPR) system with the aid of a full-duplex receiver is investigated, where the receiver acts as a friendly jammer to protect the subsequent communication activities from being detected, while transmitting radio frequency (RF) energy to charge the relay. Meanwhile, both the transmitter and the relay employ a probabilistic transmission strategy to initiate information transmission based on legitimate link information. In the multi-relay scenario, two relay scheduling schemes are proposed, namely, energy harvesting maximization scheduling (EHMS) scheme and first-hop link priority scheduling (FLPS) scheme. Then, we derive the minimum detection error probability (DEP) of the eavesdropper (Eve) in two phases, and conduct a thorough analysis of the covert performance of each scheme, including covert rate, covert energy efficiency (CEE) as well as covert outage probability (COP), and obtain the optimal transmission prior probability and the optimal jamming power under each scheme. The numerical results show that the proposed probabilistic transmission strategy can significantly enhance CEE compared to the conventional continuous transmission strategy. Moreover, the proposed transmission scheme is indeed effective in enhancing the covert performance, especially when there are significant differences in channel conditions between the two-hop links.

Federated learning (FL) enables the training of a global model using clients' local datasets, leveraging their computing resources for efficient machine learning while preserving user privacy. This paper explores FL in wireless networks, focusing on client selection and bandwidth allocation as key factors impacting latency, covert constraint and energy consumption. We propose the per-round energy drift plus cost (PEDPC) algorithm to address this optimization problem from an online perspective. The performance of the PEDPC algorithm is validated through simulations, evaluating latency and energy consumption under both IID and non-IID data distributions.

Abstract In the era of the Internet and big data, online social media platforms have been developing rapidly, which accelerate rumors circulation. Rumor detection on social media is a worldwide challenging task due to rumor’s feature of high speed, fragmental information and extensive range. Most existing approaches identify rumors based on single-layered hybrid features like word features, sentiment features and user characteristics, or multimodal features like the combination of text features and image features. Some researchers adopted the hierarchical structure, but they neither used rumor propagation nor made full use of its retweet posts. In this paper, we propose a novel model for rumor detection based on Graph Neural Networks (GNN), named Hierarchically Aggregated Graph Neural Networks (HAGNN). This task focuses on capturing different granularities of high-level representations of text content and fusing the rumor propagation structure. It applies a Graph Convolutional Network (GCN) with a graph of rumor propagation to learn the text-granularity representations with the spreading of events. A GNN model with a document graph is employed to update aggregated features of both word and text granularity, it helps to form final representations of events to detect rumors. Experiments on two real-world datasets demonstrate the superiority of the proposed method over the baseline methods. Our model achieves the accuracy of 95.7% and 88.2% on the Weibo dataset Ma et al. 2017 and the CED dataset Song et al. IEEE Trans Knowl Data Eng 33(8):3035–3047, 2019respectively.

Recently, as the traffic flow in the internet of vehicles increases, the conflict between the huge number of computing tasks and limited computation resources needs to be solved urgently. For the above situation, Mobile Cloud Computing (MCC) and Mobile Edge Computing (MEC) can usually serve as effective solutions. In this paper, we first develop a hierarchical edge computing model for time-varying mobile IoV-edge-cloud environment. Then we formulate a collaborative optimization problem to minimize the system cost by jointly optimizing offloading decision, the allocation of computation resource and bandwidth. Based on Reinforcement Learning (RL) method, we develop a Q-learning based algorithm to accomplish computation offloading and resource allocation. Numerical simulations verify the effectiveness of our proposed scheme by comparing with typical algorithms.

Mobile Edge Computing (MEC) has emerged as a promising computing paradigm in 5G networks, which can empower User Equipments (UEs) with computation and energy resources offered by migrating workloads from the UEs to the MEC servers. Although the issues of computation offloading and resource allocation in MEC have been studied with different optimization objectives, they mainly investigate quasi-static system environments, without considering the different resource requirements and time-varying system conditions in a dynamic system. In this paper, we exploit a multi-user MEC system, and investigate the task execution scheme for dynamic joint optimization of offloading decision and resource assignment. Our objective is to minimize the energy consumption of all UEs, with considering the delay constraint as well as the dynamic resource requirements of heterogeneous computation tasks. Accordingly, we formulate the problem as a mixed integer non-linear programming problem (MINLP), and propose a value iteration based Reinforcement Learning (RL) approach, named Q-Learning, to obtain the optimal policy of computation offloading and resource allocation. Simulation results demonstrate that the proposed approach can significantly decrease UEs' energy consumption in different scenarios, compared with other baseline methods.

Offloading cellular traffic through Opportunistic Mobile Networks (OMNs) is an effective way to relieve the burden of cellular networks. Providing data offloading services requires a lot of resources, and nodes in OMNs are selfish and rational, they are not willing to provide data offloading services for others without any compensation. Therefore, it is urgent to design an incentive mechanism to stimulate mobile nodes to participate in data offloading process. In this paper, we propose a Reverse Auction-based Incentive Mechanism to stimulate mobile nodes in OMNs to provide data offloading services, and take the cache management into consideration. We model the incentive-driven data offloading process as a non-linear integer programming problem, then a Greedy Helper Selection Method (GHSM) and a Caching Replacement Scheme (CRS) are proposed to solve the problem. In addition, we also propose an innovative payment rule based on the Vickrey-Clarke-groves (VCG) model to ensure the individual rationality and authenticity of the proposed algorithm. Trace-driven simulation results show that the proposed algorithm can reduce the cost of Content Service Provider (CSP) significantly in different scenarios.

HTTP video streaming over the wireless mobile network is challenging because the wireless mobile networking environment usually suffers fluctuation in available bandwidth and mobile users usually keep moving and playing streaming video simultaneously. To deal with the issue, a Quality Of Experience (QoE)-oriented adaptive HTTP video streaming control method based on MPEG-DASH over the wireless mobile networking environment was proposed in this paper. In order to get better QoE, the proposed method considers both temporal and geo concerns for estimating the available bandwidth in the future and the proposed adaptive streaming control scheme considers buffer level, video quality of the most recently downloaded segment and the estimated bandwidth to decide the video quality for the next downloaded video segment. The proposed method has been implemented in the Android system for the client side and the Linux system for the server side. The experiments shown that the proposed method can improve initial delay time, suspended time, suspended times, bitrate difference per segment, and average bitrate difference considering suspending.

One important issue in the study of Mobile Social Networks (MSNs) is to measure the centrality (importance) of nodes in networks. However, when measuring the centrality metrics in a certain time interval, the current studies in MSNs focus on analyzing static aggregation networks that do not change over time. Actually, network topology in MSNs is changing very rapidly, which is driven by natural social behavior of people. Therefore, it will not be accurate if the static aggregation network graph is used to measure centrality metrics in a period of time. In this paper, to solve this problem, we first introduce a time-ordered aggregation model, which reduces a dynamic network to a series of time-ordered networks. Then, we propose three particular time-ordered aggregation methods to measure the centrality of nodes in a certain period under two widely used centrality metrics, namely Betweenness centrality and Degree centrality. Finally, extensive trace-driven simulations are conducted to evaluate the performance of different aggregation methods. The results show that the time-ordered aggregation methods can measure the Betweenness and Degree centrality in a time interval more accurately than the Static Aggregation Method, and the Exponential Time-ordered Aggregation Method performs much better than other aggregation methods. Therefore, we recommend to use the Exponential Time-ordered Aggregation Method to measure centrality metrics in a certain time interval.