Trust aware support vector machine intrusion detection and prevention system in vehicular ad hoc networks

Shams, Erfan A.; Rızaner, Ahmet; Ulusoy, Ali Hakan

doi:10.1016/j.cose.2018.06.008

Cited by 76 publications

(39 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Guo et al [17] propose an approach that verifies information received via V2V in form of an IDS whose results are further used for decision-making. Other solutions on collaborative intrusion detection [28,35] consider only packet headers and parameters, such as packet drop rate and transfer delay, and investigate ways to exchange this information between neighboring vehicles.…”

Section: Related Workmentioning

confidence: 99%

V2C: A Trust-Based Vehicle to Cloud Anomaly Detection Framework for Automotive Systems

Rosenstatter

Olovsson

Almgren

2021

Proceedings of the 16th International Conference on Availability, Reliability and Security

View full text Add to dashboard Cite

Vehicles have become connected in many ways. They communicate with the cloud and will use Vehicle-to-Everything (V2X) communication to exchange warning messages and perform cooperative actions such as platooning. Vehicles have already been attacked and will become even more attractive targets due to their increasing connectivity, the amount of data they produce and their importance to our society. It is therefore crucial to provide cyber security measures to prevent and limit the impact of attacks.As it is problematic for a vehicle to reliably assess its own state when it is compromised, we investigate how vehicle trust can be used to identify compromised vehicles and how fleet-wide attacks can be detected at an early stage using cloud data. In our proposed V2C Anomaly Detection framework, peer vehicles assess each other based on their perceived behavior in traffic and V2X-enabled interactions, and upload these assessments to the cloud for analysis. This framework consists of four modules. For each module we define functional demands, interfaces and evaluate solutions proposed in literature allowing manufacturers and fleet owners to choose appropriate techniques. We detail attack scenarios where this type of framework is particularly useful in detecting and identifying potential attacks and failing software and hardware. Furthermore, we describe what basic vehicle data the cloud analysis can be based upon. CCS CONCEPTS• Security and privacy → Intrusion detection systems; • Computer systems organization → Embedded systems.

show abstract

Section: Related Workmentioning

confidence: 99%

V2C: A Trust-Based Vehicle to Cloud Anomaly Detection Framework for Automotive Systems

Rosenstatter

Olovsson

Almgren

2021

Proceedings of the 16th International Conference on Availability, Reliability and Security

View full text Add to dashboard Cite

show abstract

“…Recently, several works have been published related to ML for intrusion detection in VANET. For instance, Shams et al [48] proposed an approach combining the promiscuous mode for data collection and SVM for IDS in VANET. They aimed to analyze data to create a trust value for vehicles on the network as trust aware SVM-based IDS.…”

Section: Related Workmentioning

confidence: 99%

Misbehavior-Aware On-Demand Collaborative Intrusion Detection System Using Distributed Ensemble Learning for VANET

et al. 2020

View full text Add to dashboard Cite

Vehicular ad hoc networks (VANETs) play an important role as enabling technology for future cooperative intelligent transportation systems (CITSs). Vehicles in VANETs share real-time information about their movement state, traffic situation, and road conditions. However, VANETs are susceptible to the cyberattacks that create life threatening situations and/or cause road congestion. Intrusion detection systems (IDSs) that rely on the cooperation between vehicles to detect intruders, were the most suggested security solutions for VANET. Unfortunately, existing cooperative IDSs (CIDSs) are vulnerable to the legitimate yet compromised collaborators that share misleading and manipulated information and disrupt the IDSs’ normal operation. As such, this paper proposes a misbehavior-aware on-demand collaborative intrusion detection system (MA-CIDS) based on the concept of distributed ensemble learning. That is, vehicles individually use the random forest algorithm to train local IDS classifiers and share their locally trained classifiers on-demand with the vehicles in their vicinity, which reduces the communication overhead. Once received, the performance of the classifiers is evaluated using the local testing dataset in the receiving vehicle. The evaluation values are used as a trustworthiness factor and used to rank the received classifiers. The classifiers that deviate much from the box-and-whisker plot lower boundary are excluded from the set of the collaborators. Then, each vehicle constructs an ensemble of weighted random forest-based classifiers that encompasses the locally and remotely trained classifiers. The outputs of the classifiers are aggregated using a robust weighted voting scheme. Extensive simulations were conducted utilizing the network security laboratory-knowledge discovery data mining (NSL-KDD) dataset to evaluate the performance of the proposed MA-CIDS model. The obtained results show that MA-CIDS performs better than the other existing models in terms of effectiveness and efficiency for VANET.

show abstract

“…In addition, new branches of research allow us to innovate such as [33], which takes advantage of the fact that VANETs emissions are made using a modification of network in a promiscuous state to obtain all the data over VANETs and through algorithms of Support Vector Machine (SVM) using for data analysis to establish a shared trust value for every vehicle on the network as Trust Aware SVM-Based IDS (TSIDS). Another example of different technologies for the detection of intrusions in the system is raised in [34], which uses Artificial Neural Network (ANN) trained to be able to detect different types of attacks on networks.…”

Section: Detection and Correction Of Malicious Datamentioning

confidence: 99%

A Review of Security Aspects in Vehicular Ad-Hoc Networks

2019

View full text Add to dashboard Cite

In recent years, cooperative systems have been gaining relevance in autonomous driving to such an extent that they are necessary to reach the final goal, the autonomous car. But the relevance that the Vehicular Ad-hoc NETworks (VANETs) have acquired shows that it is still an immature technology and needs more time to develop. Proof of this is that most of these systems do not provide real security in communications; so the scientific community has tried to develop new technologies to allow greater security in this type of communications. Therefore, in this paper, a review of how the technology has evolved to maintain safety in the VANETs will be carried out; in addition, a breakdown of the different security technologies grouped by their type and the advantages and disadvantages of each one.

show abstract

Trust aware support vector machine intrusion detection and prevention system in vehicular ad hoc networks

Cited by 76 publications

References 11 publications

V2C: A Trust-Based Vehicle to Cloud Anomaly Detection Framework for Automotive Systems

V2C: A Trust-Based Vehicle to Cloud Anomaly Detection Framework for Automotive Systems

Misbehavior-Aware On-Demand Collaborative Intrusion Detection System Using Distributed Ensemble Learning for VANET

A Review of Security Aspects in Vehicular Ad-Hoc Networks

Contact Info

Product

Resources

About