AI-Based Intrusion Detection Systems for In-Vehicle Networks: A Survey

Rajapaksha, Sampath; Kalutarage, Harsha; Al-Kadri, M. Omar; Petrovski, Andrei; Madzudzo, Garikayi; Cheah, Madeline

doi:10.1145/3570954

Cited by 55 publications

(29 citation statements)

References 156 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These major enablers have been investigated independently in-vehicle networks. 10 In their study, the authors developed an integrated framework to increase the performance of next-generation vehicle networks. 11 Their paradigm presented resource allocation as a combined optimization problem considering networking, caching, and computation advantages.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Information and communications technology have fueled linked automobiles' networking, caching, and computing improvements. These major enablers have been investigated independently in‐vehicle networks 10 . In their study, the authors developed an integrated framework to increase the performance of next‐generation vehicle networks 11 .…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent multimedia content delivery in 5G/6G networks: A reinforcement learning approach

Iqbal

Farhan

Ullah

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Multimedia content in 5G/6G networks makes safe, confidential, and efficient content delivery difficult. Intelligent systems that adapt to the ever‐changing network environment are needed to distribute multimedia content in these networks. Reinforcement learning (RL) can optimize multimedia content distribution based on network congestion, capacity, and user preferences. This study proposes RL‐based intelligent multimedia content distribution. RL algorithms learn from the network environment and generate optimum judgments incorporating several aspects of the suggested framework. The framework delivers multimedia material securely and privately with great quality. This study provides an intelligent multimedia content delivery architecture that uses RL approaches to solve 5G/6G content delivery problems. This research presents an RL system optimized with the double DQN algorithm having a reward of 51604.93 in 7000 episodes for efficient video file sharing on intracity buses. The RL agent balances network congestion and bandwidth by leveraging multiple sources such as bus and intersection caches and base stations, improving secure multimedia content delivery in 5G/6G networks and enhancing the passenger experience. The study confirms the system's effectiveness using reward and loss metrics and identifies potential future research directions. Future work could explore additional RL algorithms, scalability for larger networks, complex delivery scenarios, and integration with blockchain and edge computing for improved security and efficiency in multimedia content delivery.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Intelligent multimedia content delivery in 5G/6G networks: A reinforcement learning approach

Iqbal

Farhan

Ullah

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…Recently, the Internet of Vehicles (IoV) has been widely criticized for the vulnerability of its communication protocols, which made several security threats, such as authentication hijacking, message tapping, and availability destruction [1]. These are mainly caused by the Controller Area Network(CAN), considered the de facto standard for in-vehicle communication [2], [3].…”

Section: Introductionmentioning

confidence: 99%

Meta-IDS: Meta-Learning Automotive Intrusion Detection Systems with Adaptive and Learnable

Wang,

Li,

Huang

et al. 2024

Preprint

View full text Add to dashboard Cite

In the rapidly evolving landscape of vehicular communications, the widespread use of the Controller Area Network (CAN) in modern vehicles has revealed significant security vulnerabilities. However, existing Intrusion Detection Systems (IDS) struggle to adapt to varied attack scenarios and precisely detect low-volume attacks. In this paper, we introduce a novel IDS that employs meta-learning via the Meta-SGD algorithm, enhancing adaptability across a diverse spectrum of cyber threats, called Meta-IDS. Specifically, our methodology includes a bi-level optimization technique where the inner level focuses on optimizing detection accuracy for specific attack scenarios, and the outer level adjusts meta-parameters to ensure generalizability across different scenarios. For modeling low-volume attacks, we devise the Attack Prominence Score (APS), identifying subtle attack patterns with a threshold of APS \(\textgreater\) 7, allowing for precise differentiation of these attacks. The extensive experiment results show that the proposed method facilitates efficient tuning and rapid adaptation for different modeling paradigms in few-shot scenarios. The detection performance is exceptional, with F1-scores reaching 100% across most attack scenarios, including low-volume attacks. Also, the real-time vehicle-level evaluations demonstrate its adaptability for the vehicular networks.

show abstract

“…technologies integrated into vehicles, ICVs can obtain various intelligent services and comfortable experiences, including autonomous driving, collision avoidance, auto parking assist, and so on. However, these technologies also expose the invehicle network to attackers with more opportunities, and a large number of evolving new types of attacks have appeared in cyberspace, which threatenes the security of in-vehicle network (IVN) and even the safety of passengers [2].…”

Section: Introductionmentioning

confidence: 99%

“…Ecryption and authentication methods are effective for protecting IVNs [5], but it is generally necessary to add specific hardware to ensure the efficiency of encryption and decryption. As another security way, intrusion detection method does not require modification of the CAN protocol message fields and interactions, which has broader applicability for resource-constrained IVN environments [8].…”

Section: Introductionmentioning

confidence: 99%