DAG-based swarm learning: A secure asynchronous learning framework for Internet of Vehicles

To provide diversified services in the intelligent transportation systems, smart vehicles will generate unprecedented amounts of data every day. Due to data security and user privacy issues, Federated Learning (FL) is considered a potential solution to ensure privacy-preserving in data sharing. Howe...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoge Huang, Hongbo Yin, Qianbin Chen, Yu Zeng, Jianfeng Yao
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2024-12-01
Series:Digital Communications and Networks
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352864823001578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846101670320144384
author Xiaoge Huang
Hongbo Yin
Qianbin Chen
Yu Zeng
Jianfeng Yao
author_facet Xiaoge Huang
Hongbo Yin
Qianbin Chen
Yu Zeng
Jianfeng Yao
author_sort Xiaoge Huang
collection DOAJ
description To provide diversified services in the intelligent transportation systems, smart vehicles will generate unprecedented amounts of data every day. Due to data security and user privacy issues, Federated Learning (FL) is considered a potential solution to ensure privacy-preserving in data sharing. However, there are still many challenges to applying the traditional synchronous FL directly in the Internet of Vehicles (IoV), such as unreliable communications and malicious attacks. In this paper, we propose a Directed Acyclic Graph (DAG) based Swarm Learning (DSL), which integrates edge computing, FL, and blockchain technologies to provide secure data sharing and model training in IoVs. To deal with the high mobility of vehicles, the dynamic vehicle association algorithm is introduced, which could optimize the connections between vehicles and road side units to improve the training efficiency. Moreover, to enhance the anti-attack property of the DSL algorithm, a malicious attack detection method is adopted, which could recognize malicious vehicles by the site confirmation rate. Furthermore, an accuracy-based reward mechanism is developed to promote vehicles to participate in the model training with honest behaviors. Finally, simulation results demonstrate that the proposed DSL algorithm could achieve better performance in terms of model accuracy, convergence rates and security compared with existing algorithms.
format Article
id doaj-art-f8bcdc9f4dda4809a43392fdebbcc7b2
institution Kabale University
issn 2352-8648
language English
publishDate 2024-12-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Digital Communications and Networks
spelling doaj-art-f8bcdc9f4dda4809a43392fdebbcc7b22024-12-29T04:47:34ZengKeAi Communications Co., Ltd.Digital Communications and Networks2352-86482024-12-0110616111621DAG-based swarm learning: A secure asynchronous learning framework for Internet of VehiclesXiaoge Huang0Hongbo Yin1Qianbin Chen2Yu Zeng3Jianfeng Yao4School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China; Corresponding author.School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, 400065, ChinaSchool of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, 400065, ChinaShanghai Cygnus Semiconductor Co., Ltd., Shanghai, ChinaChongqing Changan Automobile Co., Ltd., Chongqing, ChinaTo provide diversified services in the intelligent transportation systems, smart vehicles will generate unprecedented amounts of data every day. Due to data security and user privacy issues, Federated Learning (FL) is considered a potential solution to ensure privacy-preserving in data sharing. However, there are still many challenges to applying the traditional synchronous FL directly in the Internet of Vehicles (IoV), such as unreliable communications and malicious attacks. In this paper, we propose a Directed Acyclic Graph (DAG) based Swarm Learning (DSL), which integrates edge computing, FL, and blockchain technologies to provide secure data sharing and model training in IoVs. To deal with the high mobility of vehicles, the dynamic vehicle association algorithm is introduced, which could optimize the connections between vehicles and road side units to improve the training efficiency. Moreover, to enhance the anti-attack property of the DSL algorithm, a malicious attack detection method is adopted, which could recognize malicious vehicles by the site confirmation rate. Furthermore, an accuracy-based reward mechanism is developed to promote vehicles to participate in the model training with honest behaviors. Finally, simulation results demonstrate that the proposed DSL algorithm could achieve better performance in terms of model accuracy, convergence rates and security compared with existing algorithms.http://www.sciencedirect.com/science/article/pii/S2352864823001578Direct acyclic graphInternet of VehiclesSwarm learningAsynchronous learning
spellingShingle Xiaoge Huang
Hongbo Yin
Qianbin Chen
Yu Zeng
Jianfeng Yao
DAG-based swarm learning: A secure asynchronous learning framework for Internet of Vehicles
Digital Communications and Networks
Direct acyclic graph
Internet of Vehicles
Swarm learning
Asynchronous learning
title DAG-based swarm learning: A secure asynchronous learning framework for Internet of Vehicles
title_full DAG-based swarm learning: A secure asynchronous learning framework for Internet of Vehicles
title_fullStr DAG-based swarm learning: A secure asynchronous learning framework for Internet of Vehicles
title_full_unstemmed DAG-based swarm learning: A secure asynchronous learning framework for Internet of Vehicles
title_short DAG-based swarm learning: A secure asynchronous learning framework for Internet of Vehicles
title_sort dag based swarm learning a secure asynchronous learning framework for internet of vehicles
topic Direct acyclic graph
Internet of Vehicles
Swarm learning
Asynchronous learning
url http://www.sciencedirect.com/science/article/pii/S2352864823001578
work_keys_str_mv AT xiaogehuang dagbasedswarmlearningasecureasynchronouslearningframeworkforinternetofvehicles
AT hongboyin dagbasedswarmlearningasecureasynchronouslearningframeworkforinternetofvehicles
AT qianbinchen dagbasedswarmlearningasecureasynchronouslearningframeworkforinternetofvehicles
AT yuzeng dagbasedswarmlearningasecureasynchronouslearningframeworkforinternetofvehicles
AT jianfengyao dagbasedswarmlearningasecureasynchronouslearningframeworkforinternetofvehicles