Machine Learning for Security in Vehicular Networks: A Comprehensive Survey

Talpur, Anum; Gurusamy, Mohan

doi:10.1109/comst.2021.3129079

Cited by 46 publications

(28 citation statements)

References 185 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid hacking and car theft, the vehicle must ensure that the driver's identity and profile are valid. A recent study carried out by Talpur and Gurusamy [176] to categorize ML techniques based on their utilization in V2X applications and methodologies, along with the working principles of these ML techniques in solving various security concerns, including attacks, privacy, trust, intrusion detection, and driver identification/fingerprinting, were reviewed. Not long ago, Martinelli et al [177] demonstrated how ML algorithms may help distinguish between genuine automobile owners and reprobates using features from the CAN.…”

Section: G Vehicular Forensicsmentioning

confidence: 99%

Application of Artificial Intelligence to Network Forensics: Survey, Challenges and Future Directions

et al. 2022

View full text Add to dashboard Cite

Network forensics focuses on the identification and investigation of internal and external network attacks, the reverse engineering of network protocols, and the uninstrumented investigation of networked devices. It lies at the intersection of digital forensics, incident response and network security. Network attacks exploit software and hardware vulnerabilities and communication protocols. The scope of a network forensic investigation can range from Internet-wide down to a single device's network traffic. Network analysis tools (NATs) aid security professionals and law enforcement in the capturing, identification and analysis of network traffic. However, in most instances, the sheer volume of data to be analyzed is enormous and, despite some built-in NAT automation, the investigation of network traffic is often an arduous process. Furthermore, significant expert time remains wasted in the investigation of a high frequency of false positive alerting from automated systems. To address this globally impacting problem, artificial intelligence based approaches are becoming increasingly employed to automatically detect attacks and increase network traffic classification accuracy. This paper provides a comprehensive survey of the state-of-the-art in network forensics and the application of expert systems, machine learning, deep learning, and ensemble/hybrid approaches to a range of application areas in the field. These include network traffic analysis, intrusion detection systems, Internetof-Things devices, cloud forensics, DNS tunneling, smart grid forensics, and vehicle forensics. In addition, the current challenges and future research directions for each of the aforementioned application areas is discussed.

show abstract

Section: G Vehicular Forensicsmentioning

confidence: 99%

Application of Artificial Intelligence to Network Forensics: Survey, Challenges and Future Directions

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The continuous interaction of DRL with the environment makes it more vulnerable than other ML techniques. Data poisoning attacks like label flipping, backdoor attack, and model poisoning attack are very common adversarial attacks on DRL and are explored in the literature for IoV applications [3]. In a recent work, the authors provide a comprehensive survey on various attacks on DRL [6].…”

Section: Related Workmentioning

confidence: 99%

“…Specifically, we propose an attack detection framework against Sybil-based data poisoning attacks in the context of DRL-based mechanisms in IoV applications. Several adversarial data poisoning attacks like adversarial random noises, data flipping and backdoor attacks, are common and explored in the literature for vehicular applications [3], [6]. Different from the existing works, we use Sybil-based adversarial attacks.…”

Section: B Attack Modelmentioning

confidence: 99%

GFCL: A GRU-based Federated Continual Learning Framework against Adversarial Attacks in IoV

Talpur¹,

Gurusamy²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The integration of ML in 5G-based Internet of Vehicles (IoV) networks has enabled intelligent transportation and smart traffic management. Nonetheless, the security against adversarial attacks is also increasingly becoming a challenging task. Specifically, Deep Reinforcement Learning (DRL) is one of the widely used ML designs in IoV applications. The standard ML security techniques are not effective in DRL where the algorithm learns to solve sequential decision-making through continuous interaction with the environment, and the environment is time-varying, dynamic, and mobile. In this paper, we propose a Gated Recurrent Unit (GRU)-based federated continual learning (GFCL) anomaly detection framework against adversarial attacks in IoV. The objective is to present a lightweight and scalable framework that learns and detects the illegitimate behavior without having a-priori training dataset consisting of attack samples. We use GRU to predict a future data sequence to analyze and detect illegitimate behavior from vehicles in a federated learning-based distributed manner. We investigate the performance of our framework using real-world vehicle mobility traces. The results demonstrate the effectiveness of our proposed solution for different performance metrics.

show abstract

“…Predicting the position of the vehicle is difficult • Rapidly Changing network topology: In VANETs, as vehicles travel at a random pace and in diverse directions, the location of vehicles will vary greatly due to their speed and motion. Within a short amount of time, nodes might leave/join the network and it directly affects the network topology • Unlimited battery power: Vehicles in MANETs travel with their batteries, so the network components don't have to rely on a restricted power source to perform effectively • Unbounded Network size: The size of a network is not restricted to a certain range • Frequent Exchange of Information: Real-time information captured in the network is required to be exchanged among vehicles and Road Side Units (RSUs) on a frequent basis to take important runtime decisions with minimum errors • Wireless communication: Vehicles are wirelessly connected with one another and with the RSUs to facilitate the exchange of information within the network • Time Critical: As vehicle driving is a time-sensitive application, it is required to minimize the delay in data transfer and hence, the information must be provided to the vehicles within a certain time frame • Physical protection: Vehicles are considered network nodes in VANETs and hence, their physical safety is also important for uninterrupted network operations [9]. Adversaries might attempt to make a physical compromise by launching physical attacks on the nodes…”

Section: Characteristics Of Vanetsmentioning

confidence: 99%

Routing Protocols and Security Issues in Vehicular Ad hoc Networks: A Review

Khanpara

Bhojak

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Vehicular Ad hoc Networks, also known as VANETs, are temporary wireless networks consisting of different types of automobiles as network nodes and the connections among these vehicles as links. VANET is a booming technology that has become quite popular in research, academia, and industry domains. A VANET can be considered as a moving network in which the nodes are automobiles. As VANETs are basically ad hoc networks, they have all the fundamental characteristics of ad hoc networks including computational and storage constraints. A network of VANETs can also be formed to enhance the safety and other services for vehicle drivers. VANETs are proven to be efficient in many real-life scenarios including traffic control and driver assistance. Information communicated through VANETs can definitely help to improve the user driving experience and avoid collisions. This paper discusses various deployment scenarios for VANETs along with the communication requirements and security concerns.

show abstract

Machine Learning for Security in Vehicular Networks: A Comprehensive Survey

Cited by 46 publications

References 185 publications

Application of Artificial Intelligence to Network Forensics: Survey, Challenges and Future Directions

Application of Artificial Intelligence to Network Forensics: Survey, Challenges and Future Directions

GFCL: A GRU-based Federated Continual Learning Framework against Adversarial Attacks in IoV

Routing Protocols and Security Issues in Vehicular Ad hoc Networks: A Review

Contact Info

Product

Resources

About