When Trust Meets the Internet of Vehicles: Opportunities, Challenges, and Future Prospects

Mahmood, Adnan; Sheng, Quan Z.; Siddiqui, Sarah; Sagar, Subhash; Zhang, Wei Emma; Suzuki, Hideyuki; Ni, Wei

doi:10.1109/cic52973.2021.00018

Cited by 14 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The trust degree of nodes is calculated by weighted average. In [32], the main difficulty of an entity-based trust model maintaining the trust relationship between vehicles lies in how to collect enough information to evaluate the trust degree of nodes, especially when vehicles have just joined VANET. Additionally, when there is not enough interactive information, or there are few connections between vehicles and short communication links, e.g., in suburbs with sparse vehicles, these factors can make it difficult to evaluate trust effectively.…”

Section: Entity-based Trust Model (Etm)mentioning

confidence: 99%

Towards Strengthening the Resilience of IoV Networks—A Trust Management Perspective

et al. 2022

View full text Add to dashboard Cite

Over the past decade or so, considerable and rapid advancements in the state of the art within the promising paradigms of the Internet of Things (IoT) and Artificial Intelligence (AI) have accelerated the development of conventional Vehicular Ad Hoc Networks (VANETS) into the Internet of Vehicles (IoV), thereby bringing both connected and autonomous driving much closer to realization. IoV is a new concept in the Intelligent Traffic System (ITS) and an extended application of IoV in intelligent transportation. It enhances the existing capabilities of mobile ad hoc networks by integrating them with IoT so as to build an integrated and unified vehicle-to-vehicle network. It is worth mentioning that academic and industrial researchers are paying increasing attention to the concept of trust. Reliable trust models and accurate trust assessments are anticipated to improve the security of the IoV. This paper, therefore, focuses on the existing trustworthiness management models along with their corresponding trust parameters, as well as the corresponding trust evaluation parameters and simulation, which provide the basis for intelligent and efficient model suggestions and optimal parameter integration. In addition, this paper also puts forward some open research directions that need to be seriously solved before trust can play its due role in enhancing IoV network elasticity.

show abstract

Section: Entity-based Trust Model (Etm)mentioning

confidence: 99%

Towards Strengthening the Resilience of IoV Networks—A Trust Management Perspective

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Therefore, it is of paramount importance to design an efficient participant selection approach for reliable model training. Reputation is a metric to evaluate trustworthiness of entities based on their past interactions [14][15][16]. Recently, a couple of studies employed reputation as a metric to select reliable devices for participating in FL process.…”

Section: Participant Selection In Flmentioning

confidence: 99%

A Survey on Participant Selection for Federated Learning in Mobile Networks

Soltani¹,

Haghighi²,

Mahmood³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Federated Learning (FL) is an efficient distributed machine learning paradigm that employs private datasets in a privacypreserving manner. The main challenges of FL are that end devices usually possess various computation and communication capabilities and their training data are not independent and identically distributed (non-IID). Due to limited communication bandwidth and unstable availability of such devices in a mobile network, only a fraction of end devices (also referred to as the participants or clients in a FL process) can be selected in each round. Hence, it is of paramount importance to utilize an efficient participant selection scheme to maximize the performance of FL including final model accuracy and training time. In this paper, we provide a review of participant selection techniques for FL. First, we introduce FL and highlight the main challenges during participant selection. Then, we review the existing studies and categorize them based on their solutions. Finally, we provide some future directions on participant selection for FL based on our analysis of the state-of-the-art in this topic area. CCS CONCEPTS• Computing methodologies → Machine learning; Distributed computing methodologies.

show abstract

“…As shown in Figure 1, IoV can make use of vehicular wireless communication devices to realize vehicle-to-vehicle (V2V), vehicle-to-pedestrian (V2P), and vehicle-to-infrastructure (V2I) communication and transmit data to the Cloud through the base station [5]. However, due to the complex and changeable communication environment, the interruption of communication links and the loss of device status information meet extreme challenges [6]. With the help of artificial intelligence (AI), neural networks (NN) are combined with IoV to form a complete communication system to enhance the intelligence of the traffic system.…”

Section: Introductionmentioning

confidence: 99%

Outage performance prediction of cooperative vehicle network based on sparrow search algorithm based on back‐propagation neural network

Li,

Zhang,

Tian

et al. 2023

IET Networks

View full text Add to dashboard Cite

With the support of the sixth‐generation mobile networks (6G) technology, the Internet‐of‐Vehicle (IoV) can realize the perception and monitoring of vehicle road information. However, due to the change of network topology and various environment, the reliable performance of the communication link is facing challenges. For the sake of improving communication quality, a cooperative vehicular network (CVN) system is established, which adopts cooperative communication and multiple input multiple output (MIMO) technology. According to the signal‐to‐noise ratio (SNR) threshold of relay vehicles, using hybrid decode‐amplify‐forward (HDAF) protocol and combining with antenna selection, the analytical expression of outage probability (OP) with Meijer‐G function is obtained. For predicting the OP accurately, the sparrow search algorithm based on back‐propagation neural network (SSA‐BPNN) is put forward. The simulation results show that the cascade order of the channels has a negative effect on the OP. Meanwhile, the prediction accuracy of SSA‐BPNN is 64.8% higher than that of BPNN, and 98.96% greater than that of general regression neural network, and the convergence rate is faster than ICS‐BPNN.

show abstract

When Trust Meets the Internet of Vehicles: Opportunities, Challenges, and Future Prospects

Cited by 14 publications

References 33 publications

Towards Strengthening the Resilience of IoV Networks—A Trust Management Perspective

Towards Strengthening the Resilience of IoV Networks—A Trust Management Perspective

A Survey on Participant Selection for Federated Learning in Mobile Networks

Outage performance prediction of cooperative vehicle network based on sparrow search algorithm based on back‐propagation neural network

Contact Info

Product

Resources

About