A Survey of the Social Internet of Vehicles: Secure Data Issues, Solutions, and Federated Learning

Xing, Ling; Zhao, Pengcheng; Gao, Jianping; Wu, Honghai

doi:10.1109/mits.2022.3190036

Cited by 14 publications

(7 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jamil et al [38] explore the application of digital twin (DT) and FL in various contexts such as industrial IoT (IIoT), IoV, and the Internet of Drones (IoD). Under the topic of IoV security and privacy issues, Hussain et al [39] discuss cybersecurity and privacy issues in Connected and Autonomous Vehicles (CAVs) under an FL architecture, while Xing et al [40] elaborate on the attack model of the Social Internet of Vehicles (SloV) and provide a comparative analysis of typical data security solutions, emphasizing the synergy of federated learning in data security protection. Other studies focus on the integration of blockchain and FL in ITS.…”

Section: A Current State Of Art and Our Contributionsmentioning

confidence: 99%

“…Similarly, studies by Zhu et al [41] and Billah et al [37] concentrate on blockchain-assisted FL architectures and do not comprehensively cover other assistive technologies. The works by Hussain et al [39] and Xing et al [40] solely discuss the advantages of FL in terms of privacy protection and security. Finally, with the exception of Billah et al [37] and Chellapandi et al [43], the other articles lack organization based on ITS task scenarios, which hinders the reader's intuitive understanding of FL-enabled ITS.…”

Section: A Current State Of Art and Our Contributionsmentioning

confidence: 99%

“…Only the role of blockchain as a supporting mechanism is discussed. [40] 2023 ✓ ✗ Social Internet of Vehicles (SloV), data security solutions, FL synergistic.…”

Section: A Current State Of Art and Our Contributionsmentioning

confidence: 99%

See 2 more Smart Citations

Enhanced Federated Learning for Edge Data Security in Intelligent Transportation Systems

Zhu

Yin

et al. 2023

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Section: A Current State Of Art and Our Contributionsmentioning

confidence: 99%

Section: A Current State Of Art and Our Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Federated Learning for Edge Data Security in Intelligent Transportation Systems

Zhu

Yin

et al. 2023

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

“…Secondly, these schemes usually require devices to have powerful computing capabilities, so they are usually trained in the cloud, and vehicle-related data needs to be uploaded to the cloud. During this process, the user's privacy data, such as location information, behavior habits, and consumption records, are also uploaded, which can easily lead to user privacy leakage problems [9,10].…”

Section: Introductionmentioning

confidence: 99%

FL-MAAE: An Intrusion Detection Method for the Internet of Vehicles Based on Federated Learning and Memory-Augmented Autoencoder

Xing

Wang

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

The Internet of Vehicles (IoV) is a network system that enables wireless communication and information exchange between vehicles and other traffic participants. Intrusion detection plays a very important role in the IoV. However, with the development of the IoV, unknown attack behaviors may appear. The lack of analysis and collection of these attack behavior has led to an imbalance in the sample data categories of the IoV intrusion detection, which causes the problem of low detection accuracy. At the same time, the intrusion detection model usually needs to upload data to the cloud for training, which will introduce the privacy risk due to of the leakage of vehicle users’ information. In this paper, we propose an intrusion detection method for the IoV based on federated learning and memory-augmented autoencoder (FL-MAAE). We add a memory module to the autoencoder model to enhance its ability to store the behavior feature patterns of the IoV, make it robust to imbalanced samples, and use the reconstruction error as the evaluation index, so as to detect unknown attacks in the IoV. We propose a federated learning based training method for the IoV intrusion detection model. Local training of intrusion detection models in roadside units can effectively protect the privacy of data resources. We also designed an aggregation method based on the performance contribution of participants to improve the reliability of model aggregation. We conducted experiments on the NSL-KDD intrusion detection dataset to evaluate the performance of the proposed method. Experimental results show that our method has the best intrusion detection performance. In the case of contaminated samples, the accuracy and F1 score of the proposed method are 9.6% and 7.39% higher than those of the comparison methods on average.

show abstract

“…In [4], the authors introduced the concept of federated learning, demonstrating how it can provide privacy by design, in addition to the benefit of using real-world, distributed data for model training. Subsequent works have further explored the possibilities of federated learning in different contexts, including healthcare, telecommunications, and the Internet of Things (IoT) [5]. Among these applications, integrating federated learning with vehicular communications has been a topic of considerable interest.…”

mentioning

confidence: 99%

Federated Learning for Secure and Efficient Vehicular Communications in Open RAN

Asad,

Shaukat,

Nakazato

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper presents a comprehensive exploration of federated learning applied to vehicular communications within the context of Open RAN. Through an in-depth review of existing literature and analysis of fundamental concepts, critical challenges are identified within the current methodologies employed in this sphere. A novel framework is proposed to address these shortcomings, fundamentally based on federated learning principles. This framework aims to enhance security and efficiency in vehicular communications, leveraging the flexibility of Open RAN architecture. The paper further delves into a rigorous justification of the proposed solution, highlighting its potential impact and the improvements it could bring to vehicular communications. Ultimately, this study provides a roadmap for future research in applying federated learning for more secure and efficient vehicular communications in Open RAN, opening up new avenues for exploration in this exciting interdisciplinary domain.

show abstract

A Survey of the Social Internet of Vehicles: Secure Data Issues, Solutions, and Federated Learning

Cited by 14 publications

References 91 publications

Enhanced Federated Learning for Edge Data Security in Intelligent Transportation Systems

Enhanced Federated Learning for Edge Data Security in Intelligent Transportation Systems

FL-MAAE: An Intrusion Detection Method for the Internet of Vehicles Based on Federated Learning and Memory-Augmented Autoencoder

Federated Learning for Secure and Efficient Vehicular Communications in Open RAN

Contact Info

Product

Resources

About