Generative artificial intelligence (GAI), e.g., diffusion model is recognized as a promising paradigm for enhancing intelligent transportation systems in vehicular networks. However, the existing implementation of GAI in vehicular networks is limited due to the massive data requirements of GAI and the considerable resources for model training, particularly in distributed vehicular network environments. Federated learning (FL) offers a promising solution by enabling distributed collaborative training for GAI. Therefore, in this paper we present an FL-empowered diffusion model training scheme for vehicular networks. Specifically, first, a novel utility evaluation model based on local model training accuracy is designed to assess the contribution of each vehicle's local model. The interactions between the edge computing servers and vehicles are modeled using a Stackelberg game, while a non-cooperative game determines the optimal strategy among vehicles. To account for the heterogeneity of vehicles and the uncertainty of associated risks, we incorporate prospect theory (PT) to represent subjective utility. Afterward, a backward induction mechanism is devised to determine the Stackelberg equilibrium for deriving the optimal decisions of edge computing servers and vehicles. Finally, simulations are conducted to illustrate that the proposed scheme significantly improves the sum utility rate in comparison to other baseline schemes.

Federated learning is a collaborative training paradigm designed to protect private data and is widely used in the cooperative training of Internet of Things (IoT) devices. However, despite its focus on privacy protection, federated learning remains susceptible to poisoning attacks from malicious clients. These attacks can degrade system performance and potentially lead to data privacy breaches. Moreover, real-world IoT datasets are often heterogeneous, further increasing the difficulty of detecting malicious clients. Existing defense mechanisms often struggle to effectively identify malicious clients while maintaining high model performance. To address this issue, we propose a defense mechanism called Malicious client exclusion aggregation (MaEA). This method utilizes KL divergence to preliminarily filter out anomalous clients, aggregates the remaining (preliminarily filtered) clients to obtain a pre-center model, and then identifies and excludes malicious clients by measuring their deviations from this pre-center model. We executed a series of extensive experiments on the CIFAR-10 dataset to demonstrate the effectiveness of MaEA. The results demonstrate that our approach can efficiently detect and identify malicious clients while correcting model performance.

Network Intrusion Detection Systems (NIDS) have been established as a valuable tool for analyzing network traffic to identify malicious activity. Machine learning techniques have been employed in the creation of network intrusion detection systems. While machine learning techniques have been able to improve NIDS’s performance, the use of such techniques leaves an NIDS vulnerable to adversarial example attacks. In this paper, we explore this vulnerability against a NIDS, Whisper, based on the Kitsune Surveillance Network Intrusion Dataset. The NIDS is attacked with temporal-spatial adversarial examples generated in four different ways. These adversarial examples include different combinations of modifications, such as adding no-op bytes to the IPv4 packet headers, as well as small random, fixed, or lossinformed perturbations to the timestamp of the packet. Our experiments demonstrate that while spatial-only modifications can degrade the NIDS’s performance by up to 10 units in the area under the ROC curve, the combination of loss-informed packet header and timestamp modification can further degrade this by up to 15 units. These findings highlight significant vulnerabilities in ML-based NIDS and suggest the need for more robust defenses against combined temporal-spatial adversarial attacks.

Recently, quantum federated learning (QFL) is advocated to leverage the robust computing power of quantum edge computing devices (QECDs) within unmanned aerial vehicle (UAV)-assisted wireless networks, to enhance the efficiency of distributed learning. However, the presence of malicious and selfish behaviors among some QECDs poses significant challenges for QFL model training to achieve high accuracy and rapid convergence. To tackle this issue, we introduce a trustenhanced incentive scheme for QFL in the UAV-assisted wireless networks. Specifically, a QECD-empowered QFL framework is first presented in the UAV-assisted wireless networks, where the QECDs independently train local models with their private data by using the quantum computing capabilities, while UAVs aggregate these trained local models to update the global model. Then, to ensure security and eliminate malicious participants, we devise a Bayesian inference-based trust assessment mechanism to select honest QECDs for local model training. Furthermore, we design a Stackelberg game-based incentive mechanism to incentivize QECDs to cooperatively provide high-quality training services. Afterwards, through game analysis using the backward induction method, we prove the existence of a Stackelberg equilibrium. The optimal payment strategies of the UAVs are obtained using the deep Q-learning network (DQN) algorithm in dynamic networks, and the optimal training contribution strategy of each QECD is derived using the convex optimization method. Finally, extensive simulations demonstrate that the proposed scheme can significantly enhance the accuracy and training speed of QFL in UAV-assisted wireless networks.

Aerial intelligent reflecting surface (AIRS), integrating unmanned aerial vehicle (UAV) with IRS, has emerged as a promising paradigm to improve the transmission quality and security in emergency communication, space-air-ground-integrated network and mobile edge computing, etc. However, the size of a single AIRS is constrained by the limited energy and payload capacity of the UAV, as well as the path loss of the air-to-ground reflective link, which makes the gain from a single AIRS finite. To address these problems, we propose a hybrid aerial IRS-assisted cooperative secure transmission system, where an aerial active IRS and an aerial simultaneously transmitting and reflecting IRS (STAR-IRS) are employed to achieve reflection amplification and 360-degree ubiquitous coverage, respectively. Additionally, the cooperative beamforming gain generated by the secondary reflection between the hybrid AIRSs can further improve communication quality. Specifically, an optimization problem is proposed with the objective of maximizing the sum secrecy rate by jointly optimizing the transmitting beamforming and the reflection coefficients of each AIRS. We first reformulated the original non-convex problem by fractional programming method, and a three-layer alternating optimization algorithm is introduced to address the proposed problem with the successive convex approximation (SCA) as well as penalty convex-concave procedure (PCCP) techniques. Finally, extensive simulations are conducted to demonstrate that the proposed scheme substantially improves the sum secrecy rate compared to other baseline schemes.

The increasing adoption of loT devices in healthcare necessitates the development of lightweight and fast intrusion de-tection systems (IDS). This paper proposes a weighted ensemble ML IDS with parallelized batch learning to optimize runtime while maintaining ML performance. The proposed method is compared to other solutions, evaluating ML performance and runtime across three different datasets. Experimental results demonstrate that although batch learning introduces feedback delay that slightly degrades ML performance, parallel computing significantly reduces runtime.

Virtual Reality (VR) paves the way to link Meta-verse and the real world, allowing users to enjoy immersive experiences. However, delivering high-quality full spherical VR service within limited rendering energy is a challenge. Mobile edge computing (MEC) is a promising paradigm to provide rendering computation services to users. It is widely held that the rendering of panoramic video presents a significant impediment in the VR system, with disregard for the importance of the data correlation leading to excessive energy consumption caused by repeated rendering. In this paper, we propose a cooperative rendering scheme in mm Wave-enabled wireless networks with MEC via a coalition formation game, among which we focus on the data correlation of the background environment of VR streams. Specifically, we first devise a multiple MEC servers rendering framework, and we formulate an optimization problem to maximize the system utility, which contains energy savings for MEC servers and users' quality of experience (QoE). Then, considering the overlap of the VR streams requested by users in Metaverse, a coalition formation game is employed to model the cooperations among MEC servers, such that the user's QoE is significantly improved. The simulation experiments show that our proposed algorithm is superior to benchmark algorithms in improving the users' QoE and reducing the total energy consumption of MEC servers.

With the rapid development of artificial intelligence technology, unmanned surface vehicles (USVs) in marine Internet of Things (MIoTs) have become an important paradigm for marine environment exploration. However, in MIoTs, when collecting environmental information, USVs face a series of threats such as engine failure, grounding and collision, etc., resulting in damage to shipboard memory, vessel breakage and sinking, which may cause loss or damage of stored data. The USV fleet consisting of multiple USVs is recently advocated to enable collaborative communication and storage resource sharing. As such, in this paper, the USV fleet-assisted data backup scheme for the damaged USVs is proposed to guarantee the availability of stored data. First, a data backup framework for USV fleets is designed, where the USVs are classified into high-risk USVs and low-risk USVs according to the damage risk probability of sailing. Within the USV fleet, high-risk USVs (i.e., requesters) back up data to low-risk USVs (i.e., assistants) under emergency time. Second, the coalition game based on cost sharing is utilized to incentivize individual USVs to form the optimal USV fleets by maximizing the expected revenues, where the cost sharing fashion effectively ensures the stability of the coalitions. Finally, the joint optimization problem of the requesters’ allocating data decisions and the assistants’ receiving data decisions is formulated to maximize the average amount of data backup. The predictor-corrector interior point method (PIPM) and Q-learning method are leveraged to derive the reasonable solution of the formulated problem, with achieving the optimal allocating data decision and receiving data decision. Extensive simulation results demonstrate that the proposed scheme outperforms the benchmark schemes in terms of individual expected revenue, participation degree and the average amount of data backup.

Federated learning (FL) is a promising distributed learning paradigm, which enables devices to collaboratively train an AI model without exposing participants' private data. However, FL is vulnerable to various attacks and thus remains exposed to privacy issues. For example, malicious parties can launch attacks to recover sensitive and private training data from the shared parameters. Leakage of privacy data can cause serious damage to data providers. Furthermore, user anonymity and data verification in FL also need to be considered. To tackle these problems, in this paper, a verifiable and privacy-preserving cooperative FL (VPPFL) scheme is proposed in UAV-assisted vehicular networks (UVNs). Specifically, to preserve the identity privacy of vehicles, elliptic curve cryptosystem (ECC) is used to generate pseudonyms for vehicles. To preserve the data privacy, Paillier homomorphic encryption algorithm is utilized to encrypt the updates of vehicles, whereby UAVs directly perform global aggregations on encrypted updates instead of raw ones. Additionally, pseudonym-based signature mechanism is presented for vehicles to generate verifiable signatures, so as to ensure the authenticity and validity of uploaded local model updates. Besides, to sufficiently use the multi-source data, multiple UAVs share the local updates packets with each other to execute global aggregation. Finally, simulations are carried out to demonstrate that the proposed scheme can achieve high accuracy and verification with providing strict privacy protection.

With the rapid advance of wireless communication technologies, the promising space-air-ground integrated networks (SAGINs) are advocated to provide ubiquitous multicast transmission services for the social community constituted by a group of mobile users that have strong social ties and similar content interests. However, due to the limited yet valuable spectrum resources, the network heterogeneity, and diverse service demands of mobile users, it is challenging to efficiently allocate bandwidth for social communities with the objective of achieving satisfactory quality of experience (QoE) in SAGINs. To address this problem, in this paper, we propose a hierarchical bandwidth allocation scheme to enable high-quality multicast services for social communities in SAGINs. Specifically, we first develop a hierarchical bandwidth allocation framework. Wherein, the low earth orbit (LEO) satellite is utilized to provide space-to-air (S2A) unicast bandwidth for unmanned aerial vehicles (UAVs) at a certain price. Each UAV is employed to provide air-to-ground (A2G) multicast bandwidth for ground social communities with a certain A2G multicast bandwidth charge. We then formulate the hierarchical bandwidth allocation problem as a four-stage Stackelberg game, where the target of each participant is to maximize its own utility. Afterward, through the game analysis by the backward induction method, the existence of the Stackelberg equilibrium is proved, where the closed-form solutions on the optimal policies of both the social communities and UAVs are derived by the convex optimization method, and the optimal pricing policies of the LEO satellite is achieved by a proposed gradient descent iteration algorithm. Finally, extensive experiments are conducted to demonstrate that the proposed scheme can greatly increase the utilities of social communities while consuming a less bandwidth compared to conventional schemes.

Autonomous vehicles (AVs) are coming with great potentials to bring safer, greener, and more convenient transportation systems. As AVs rely on radar, camera, and other advanced sensors to sense its surroundings, a salient challenge of AVs is the intrinsic limitations of onboard sensors (e.g., limited awareness range, blind spots, and failure in foggy days). To tackle this problem, we propose a collaborative data sharing scheme for AVs to make up for sensor deficiencies by promoting sensory information sharing in autonomous driving. However, this brings another fundamental issue on how to ensure trust in shared sensory data from distrustful collaborators and how to motivate AVs to participate in data sharing. This work studies this issue by modeling it as a quality-aware optimal sensing task scheduling problem. Specifically, we design an edge computing-enabled architecture where AVs can form collaborative sensing groups in executing sensing tasks. After that, a quality-aware auction-based incentive mechanism is developed to promote AVs’ participation and high-quality data sharing. We also design a reputation model to recruit trustworthy AVs to perform sensing tasks based on their behaviors and social identities. Due to the NP-hardness of problem, we devise a heuristic algorithm to determine the optimal winners and payments in auction with truthfulness and individual rationality guarantees. Lastly, extensive simulations validate that our approach can effectively improve sensing data quality and user utility, compared with conventional schemes.

Recently, unmanned aerial vehicles (UAVs) have been employed to provide wireless communication services, which promotes the emergence of promising UAV-assisted heteroge-neous networks (UHetNets). However, due to the ever-increasing amount of data traffic and diverse wireless service demands of mobile users, it is challenging to efficiently allocate limited secure bandwidth for safe communication. To tackle this problem, in this paper, we propose a game theoretical secure bandwidth allocation scheme in UHetNets. Specifically, we first design a UAV-assisted bandwidth allocation framework, where each UAV as a flying base station reuses the secure spectrum to enhance the utilization rate of wireless resource. To allocate the restricted secure band-width, we further introduce the utility functions of both UAVs and mobile users, based on the real-time bandwidth capacity of each UAV and the demand of each mobile user. Stackelberg game is then utilized to model the dynamic interactions between UAVs and mobile users. Afterwards, we devise a gradient descent based optimal decision searching algorithm to achieve the Stackelberg equilibrium. The simulation results, at last, show the effectiveness of the proposed scheme to improve the utilities of both mobile users and UAVs.

Internet-of-Things (IoT) applications have been rapidly deployed into pervasive environment, where both challenges and opportunities abound. On the one hand, a large number of IoT devices and their rich functions contribute significant volumes of data, which has brought tremendous convenience to the daily lives of end users. On the other hand, the heterogeneous IoT devices and a large amount of private information transmitted through networks also bring serious security and privacy issues. It is a big challenge to model IoT systems and trust relationships between different entities with a large number of heterogeneous IoT devices. In this article, we study a general IoT system architecture with consideration of heterogeneous IoT devices. Different trust models are proposed and analyzed based on the trust relationships between different entities in the IoT system. We propose a flexible and efficient authentication scheme with a consideration of heterogeneous IoT devices based on the least trust-required model. The proposed scheme provides security and privacy to resource-limited IoT devices flexibly and efficiently by utilizing IoT devices with better storage and computational ability. Moreover, secure data transmission is presented with contextual privacy and data integrity services. The proposed scheme achieves not only the mutual authentication, initial session key agreement, and data integrity but also anonymity, contextual privacy, forward security, end-to-end security, and key escrow resilience. Security analysis is presented to provide verification of the proposed protocol and security objectives. Moreover, performance evaluation is presented with comparison to the other schemes in terms of security features, computational overhead, and communication overhead. The performance comparisons show that our proposed scheme provides flexible and efficient security by consideration of heterogeneous IoT devices. With the higher proportion of resource-limited IoT devices, our proposed scheme outperforms other similar schemes.

In this paper, we propose identity management (IdM) framework for electronic healthcare (e-health) systems over 5G networks with consideration on wireless access and cloud access. Since 5G networks introduce new perspectives of network architecture, the IdM framework for e-health systems needs to consider different scenarios, such as different type devices with different access technologies. For the IdM based on wireless access, different access technologies are considered as direct connection based on 3GPP access and non-3GPP access and indirect connection through a smart phone. For the IdM based on cloud access, we propose two different methods including user cloud based and service provider cloud based. The comparison of these two methods are presented. The security discussion of the proposed IdM framework is provided to show the mutual authentication, identity protection and efficient security. The proposed IdM framework can achieve the required security properties efficiently in e-health system.

In this paper, we propose a heterogeneous network (HetNet) system with a cloud control center to dynamically manage small base stations (SBSs) based on traffic load. The cloud can provide a user equipment (UE) association mechanism to balance both traffic load and spectrum allocation of SBSs and the macro base station (MBS) with throughput requirements of uplink and downlink. Our proposed association mechanism and SBS management mechanism can optimize the energy efficiency (EE) of the network and UE by considering EE of both uplink and downlink. Device-to-device communications are adopted under service request probability of UE and distance limitation. The EE optimization problem is solved in two steps in this paper. First, a decoupled association for UE over uplink and downlink is adopted. Least path loss criterion is used for uplink association. And priority SBS under signal-to-interference-plus-noise rate threshold and data rate requirement is applied in downlink association. After association, the SBSs management is implemented iteratively for adjusting the operation of SBSs to maximize the EE of both the network and UE. Simulation results show that our proposed method can improve the EE of the system with better performance on offloading traffic from the MBS to SBSs.

Public safety communication aims to provide efficient mission critical and first responder communication scenarios. Device-to-device (D2D) proximity services are designed to offload massive traffic from base stations and extend the coverage area. Utilizing relay to provide network services for user equipment (UE) that out of coverage is one of the most important attributes of proximity services. Existing works mainly focus on the transmission rate and energy efficiency for relay selection. In this paper, we propose a relay selection scheme that targets to extend the connection time in public safety communications. In particular, the proposed scheme takes into consideration the remaining battery capacity and communication capability of each UE. The system level simulation results show that the proposed scheme can prolong the connection time for the UE that is out of coverage.

With the development of mobile devices, especially the emergence of smart phones, the mobile social networks (MSNs) have emerged to provide a variety of mechanisms for users to share their content. However, because the number of the mobile users still keeps growing rapidly, the MSNs become more complex than before and the features including evolution and topology need to be studied for communication system optimization. Therefore, in this paper, a great deal of data on social interactions among mobile users are collected to reveal the evolution and topological features of the MSNs. Firstly, the evolution feature of the MSN with the time is detailedly studied. Then, the statistical features of MSN including degree distribution, node distance, node closeness, and betweenness are analyzed. From the results of the analysis on the evolution features, we find that the MSN will become complex over time. In addition, the analysis of the topological properties shows that the MSN is a typical scale-free network and has strong small-world features.