AI-based Intrusion Detection for Intelligence Internet of Vehicles

Man, Dapeng; Zeng, Fanyi; Lv, Jiguang; Xuan, Shichang; Yang, Wu; Guizani, Mohsen

doi:10.1109/mce.2021.3137790

Cited by 11 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Perhaps most similar to ours is the survey composed by Man et al [118], which encompasses traditional machine learning, deep learning, and reinforcement learning IDSs for all incarnations of automotive networks. Importantly, however, it does not include non-learning IDSs, such as conventional interval-based and ID sequence-based IDSs.…”

Section: E Machine Learning and Deep Learning In Automotive Intrusion...mentioning

confidence: 91%

Intrusion Detection in the Automotive Domain: A Comprehensive Review

Lampe,

Meng

2023

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

The automotive domain has realized amazing advancements in communication, connectivity, and automationand at a breakneck pace. Such advancements come with ample benefits, such as the reduction of traffic accidents and the refinement of transit efficiency. However, these new developments were not necessarily made with security in mind. Researchers have unearthed a number of security vulnerabilities in paradigms such as in-vehicle networks (IVNs), the Internet of Vehicles (IoV), and intelligent transportation systems (ITSs). As automotive technologies continue to evolve, it would be realistic to expect new vulnerabilities to arise-both vulnerabilities that are identified and vulnerabilities that are not. If-or more pragmatically, when-these vulnerabilities are exploited, intrusion detection will be paramount.Therefore, we find it prudent to review intrusion detection in the automotive domain. We explore a myriad of threats and intrusion detection techniques-from the boundaries of the vehicle's own network to the wider Internet of Vehicles (IoV). Intrusion detection, while not a panacea, can be a costeffective solution to many automotive security issues. Generally, such intrusion detection systems (IDSs) do not disrupt existing hardware, infrastructure, or communications; rather, they merely tap into the network and monitor for suspicious traffic. Given the very reasonable price tag, the implementation of intrusion detection systems would be an auspicious step by the automotive industry to assure the security-and safety-of the modern automobile. This paper volunteers a comprehensive review of intrusion detection technologies in the automotive domain.Index Terms-Intrusion detection system (IDS), automotive, in-vehicle network (IVN), controller area network (CAN) bus, vehicular ad hoc network (VANET), Internet of Vehicles (IoV), connected and autonomous vehicles (CAVs), intelligent transportation system (ITS), deep learning (DL), machine learning (ML), blockchain

show abstract

Section: E Machine Learning and Deep Learning In Automotive Intrusion...mentioning

confidence: 91%

Intrusion Detection in the Automotive Domain: A Comprehensive Review

Lampe,

Meng

2023

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

show abstract

“…To explore potential vulnerabilities in the CAV, researchers have conducted simulations of various attack scenarios in the past. Based on the surveys [28]- [31], Table 1 provides an overview of the most common types of attacks and their corresponding descriptions.…”

Section: Related Workmentioning

confidence: 99%

FL-IDS: Federated Learning-Based Intrusion Detection System Using Edge Devices for Transportation IoT

Bhavsar,

Bekele,

Roy

et al. 2024

IEEE Access

View full text Add to dashboard Cite

A federated learning-based intrusion detection system (FL-IDS) is introduced in this paper to enhance the security of vehicular networks in the context of IoT edge device implementations. The FL-IDS system protects data privacy by using local learning, where devices share only model updates with an aggregation server. This server then generates an enhanced detection model. The FL-IDS system also incorporates machine learning (ML) and deep learning (DL) classifiers, namely logistic regression (LR) and convolutional neural networks (CNN), to prevent attacks in transportation IoT environments. The performance of the proposed IDS was evaluated using two different datasets, NSL-KDD and Car-Hacking. The model evaluation has been evaluated based on the accuracy and loss parameters. The results show that the FL-IDS system outperforms traditional centralized machine learning and deep learning approaches regarding accuracy and privacy protection.

show abstract

“…Anzel et al [ 17 ] proposed a multilayer perceptron (MLP) neural network to detect intruders or attackers on an IoV network. In addition to these, many other AI-based intrusion detection methods have been proposed in the literature as discussed by Man et al [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Efficient Dynamic Throttling Strategy for Blockchain-Based Intrusion Detection Systems in 6G-Enabled VSNs

Alevizos,

Ta,

Eiza

2023

Sensors

View full text Add to dashboard Cite

Vehicular Social Networks (VSNs) have emerged as a new social interaction paradigm, where vehicles can form social networks on the roads to improve the convenience/safety of passengers. VSNs are part of Vehicle to Everything (V2X) services, which is one of the industrial verticals in the coming sixth generation (6G) networks. The lower latency, higher connection density, and near-100% coverage envisaged in 6G will enable more efficient implementation of VSNs applications. The purpose of this study is to address the problem of lateral movements of attackers who could compromise one device in a VSN, given the large number of connected devices and services in VSNs and attack other devices and vehicles. This challenge is addressed via our proposed Blockchain-based Collaborative Distributed Intrusion Detection (BCDID) system with a novel Dynamic Throttling Strategy (DTS) to detect and prevent attackers’ lateral movements in VSNs. Our experiments showed how the proposed DTS improve the effectiveness of the BCDID system in terms of detection capabilities and handling queries three times faster than the default strategy with 350k queries tested. We concluded that our DTS strategy can increase transaction processing capacity in the BCDID system and improve its performance while maintaining the integrity of data on-chain.

show abstract

AI-based Intrusion Detection for Intelligence Internet of Vehicles

Cited by 11 publications

References 24 publications

Intrusion Detection in the Automotive Domain: A Comprehensive Review

Intrusion Detection in the Automotive Domain: A Comprehensive Review

FL-IDS: Federated Learning-Based Intrusion Detection System Using Edge Devices for Transportation IoT

A Novel Efficient Dynamic Throttling Strategy for Blockchain-Based Intrusion Detection Systems in 6G-Enabled VSNs

Contact Info

Product

Resources

About