FedAV: Federated learning for cyberattack vulnerability and resilience of cooperative driving automation

Cooperative driving automation (CDA) has gained attention over the years because of its cooperative driving capability that provides solution to individual automated driving challenges. Although reliance on communication and automation enables cooperative driving, it also introduces new cybersecurit...

Full description

Saved in:
Bibliographic Details
Main Authors: Guanyu Lin, Sean Qian, Zulqarnain H. Khattak
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Communications in Transportation Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772424725000150
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849738121214689280
author Guanyu Lin
Sean Qian
Zulqarnain H. Khattak
author_facet Guanyu Lin
Sean Qian
Zulqarnain H. Khattak
author_sort Guanyu Lin
collection DOAJ
description Cooperative driving automation (CDA) has gained attention over the years because of its cooperative driving capability that provides solution to individual automated driving challenges. Although reliance on communication and automation enables cooperative driving, it also introduces new cybersecurity threats. This study introduces a federated learning concept for autonomous and connected vehicles, known as the federated agents on vehicle platooning (FedAV) framework, which is designed to address the challenges of cyberattack simulations and anomaly detection in cooperative vehicle platooning systems. The federated learning approach was adopted because of its decentralized nature, which allows each vehicle to learn independently with the ability to overcome adversarial attacks. First, FedAV employs a mixed cyberattack simulation approach to capture complex attack patterns effectively. We tested the scalability of our approach against several attacks, including spoofing, message falsification, and replay attacks, as well as on anomalies, including short anomalies, noise anomalies, bias anomalies, and gradual shifts. In addition, our approach integrates federated learning for decentralized anomaly detection, ensuring data privacy and reducing communication overhead. The anomaly detection performance was enhanced by average and weighted aggregation strategies. Real-world scenarios from cooperative driving experiments and simulations validated the framework's effectiveness and demonstrated its potential to improve the safety, privacy, and efficiency of CDA.
format Article
id doaj-art-90e29b2617c44809aa880cb558e7b345
institution DOAJ
issn 2772-4247
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Communications in Transportation Research
spelling doaj-art-90e29b2617c44809aa880cb558e7b3452025-08-20T03:06:43ZengElsevierCommunications in Transportation Research2772-42472025-12-01510017510.1016/j.commtr.2025.100175FedAV: Federated learning for cyberattack vulnerability and resilience of cooperative driving automationGuanyu Lin0Sean Qian1Zulqarnain H. Khattak2Civil and Environmental Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213, USACivil and Environmental Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213, USATransportation and Urban Infrastructure Studies, Morgan State University, Baltimore, MD, 21251, USA; Corresponding author.Cooperative driving automation (CDA) has gained attention over the years because of its cooperative driving capability that provides solution to individual automated driving challenges. Although reliance on communication and automation enables cooperative driving, it also introduces new cybersecurity threats. This study introduces a federated learning concept for autonomous and connected vehicles, known as the federated agents on vehicle platooning (FedAV) framework, which is designed to address the challenges of cyberattack simulations and anomaly detection in cooperative vehicle platooning systems. The federated learning approach was adopted because of its decentralized nature, which allows each vehicle to learn independently with the ability to overcome adversarial attacks. First, FedAV employs a mixed cyberattack simulation approach to capture complex attack patterns effectively. We tested the scalability of our approach against several attacks, including spoofing, message falsification, and replay attacks, as well as on anomalies, including short anomalies, noise anomalies, bias anomalies, and gradual shifts. In addition, our approach integrates federated learning for decentralized anomaly detection, ensuring data privacy and reducing communication overhead. The anomaly detection performance was enhanced by average and weighted aggregation strategies. Real-world scenarios from cooperative driving experiments and simulations validated the framework's effectiveness and demonstrated its potential to improve the safety, privacy, and efficiency of CDA.http://www.sciencedirect.com/science/article/pii/S2772424725000150CybersecurityCyberattackConnected automated vehiclesAnomaly detectionFederated learningAgent
spellingShingle Guanyu Lin
Sean Qian
Zulqarnain H. Khattak
FedAV: Federated learning for cyberattack vulnerability and resilience of cooperative driving automation
Communications in Transportation Research
Cybersecurity
Cyberattack
Connected automated vehicles
Anomaly detection
Federated learning
Agent
title FedAV: Federated learning for cyberattack vulnerability and resilience of cooperative driving automation
title_full FedAV: Federated learning for cyberattack vulnerability and resilience of cooperative driving automation
title_fullStr FedAV: Federated learning for cyberattack vulnerability and resilience of cooperative driving automation
title_full_unstemmed FedAV: Federated learning for cyberattack vulnerability and resilience of cooperative driving automation
title_short FedAV: Federated learning for cyberattack vulnerability and resilience of cooperative driving automation
title_sort fedav federated learning for cyberattack vulnerability and resilience of cooperative driving automation
topic Cybersecurity
Cyberattack
Connected automated vehicles
Anomaly detection
Federated learning
Agent
url http://www.sciencedirect.com/science/article/pii/S2772424725000150
work_keys_str_mv AT guanyulin fedavfederatedlearningforcyberattackvulnerabilityandresilienceofcooperativedrivingautomation
AT seanqian fedavfederatedlearningforcyberattackvulnerabilityandresilienceofcooperativedrivingautomation
AT zulqarnainhkhattak fedavfederatedlearningforcyberattackvulnerabilityandresilienceofcooperativedrivingautomation