Collaborative Learning Based Sybil Attack Detection in Vehicular AD-HOC Networks (VANETS)

Azam, Sofia; Bibi, Maryum; Riaz, Rabia; Rizvi, Sanam Shahla; Kwon, Se Jin

doi:10.3390/s22186934

Cited by 26 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Highly dynamic connections, sensitive information sharing and time sensitivity makes VANETs architecture prone to attacks. Authors in [159] classify the attacks on VANETs, grouping the attacks in the CIA triad framework as shown in the Figure 8 below.…”

Section: Pertinent Vanet Security Issuesmentioning

confidence: 99%

Privacy and security issues surrounding vehicular Adhoc networks

Emmanuel Asituha

2023

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

Vehicular Ad-Hoc Networks (VANETs) is a type of mobile ad hoc network (MANET) specifically designed for communication among vehicles on the road. VANETs enable vehicles to communicate with each other and with roadside infrastructure, forming a dynamic and self-organizing network without the need for a fixed communication infrastructure. Security concerns in VANETs encompass a range of threats, including Authentication and Authorization attacks, Sybil attacks, Denial-of-Service incidents, Location spoofing, and Eavesdropping. Privacy, on the other hand, is a paramount concern in VANETs due to the sensitive nature of location-based data, Identity Disclosure, and user consent Control. The paper emphasizes the necessity for robust security mechanisms and outlines specific requirements for safeguarding VANETs. Proposed mitigation measures, including cryptographic techniques and authentication mechanisms, are critically assessed for their effectiveness and feasibility. The findings provide a comprehensive understanding of the complexities surrounding privacy and security in VANETs, contributing valuable insights for the development of resilient and privacy-preserving vehicular communication systems.

show abstract

Section: Pertinent Vanet Security Issuesmentioning

confidence: 99%

Privacy and security issues surrounding vehicular Adhoc networks

Emmanuel Asituha

2023

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

show abstract

“…Khan et al [23] Vermani, Noliya, Kumar, & Dutta Journal of Information Systems Engineering and Business Intelligence, 2023, 9 (2), 136-146 139 developed an ensemble-based voting classifier for intrusion detection that incorporated multiple base classifiers, showing a 96% accuracy rate for GPS detection compared to standard ML algorithm. Similarly, Azam et al [24] used majority voting to detect sybil attacks in the VANET system. Standard ML classifiers, including k-NN, Nave Bayes, Decision tree, SVM, and Logical Regression, were used within the majority voting framework, with the proposed scheme achieving a 95% degree of accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

Ensemble Learning Based Malicious Node Detection in SDN-Based VANETs

Vermani,

Noliya,

Kumar

et al. 2023

J. Inf. Syst. Eng. Bus. Intell.

View full text Add to dashboard Cite

Background: The architecture of Software Defined Networking (SDN) integrated with Vehicular Ad-hoc Networks (VANETs) is considered a practical method for handling large-scale, dynamic, heterogeneous vehicular networks, since it offers flexibility, programmability, scalability, and a global understanding. However, the integration with VANETs introduces additional security vulnerabilities due to the deployment of a logically centralized control mechanism. These security attacks are classified as internal and external based on the nature of the attacker. The method adopted in this work facilitated the detection of internal position falsification attacks. Objective: This study aimed to investigate the performance of k-NN, SVM, Naïve Bayes, Logistic Regression, and Random Forest machine learning (ML) algorithms in detecting position falsification attacks using the Vehicular Reference Misbehavior (VeReMi) dataset. It also aimed to conduct a comparative analysis of two ensemble classification models, namely voting and stacking for final decision-making. These ensemble classification methods used the ML algorithms cooperatively to achieve improved classification. Methods: The simulations and evaluations were conducted using the Python programming language. VeReMi dataset was selected since it was an application-specific dataset for VANETs environment. Performance evaluation metrics, such as accuracy, precision, recall, F-measure, and prediction time were also used in the comparative studies. Results: This experimental study showed that Random Forest ML algorithm provided the best performance in detecting attacks among the ML algorithms. Voting and stacking were both used to enhance classification accuracy and reduce time required to identify an attack through predictions generated by k-NN, SVM, Naïve Bayes, Logistic Regression, and Random Forest classifiers. Conclusion: In terms of attack detection accuracy, both methods (voting and stacking) achieved the same level of accuracy as Random Forest. However, the detection of attack using stacking could be achieved in roughly less than half the time required by voting ensemble. Keywords: Machine learning methods, Majority voting ensemble, SDN-based VANETs, Security attacks, Stacking ensemble classifiers, VANETs,

show abstract

“…Vehicular networks have been at the center of traffic management research due to the exponential increase in the world's vehicle population. With the use of various communication technologies, data can be transferred and shared among vehicles, the vehicular ad-hoc network (VANET) may be protected, and the collected data can be used to improve road safety and other areas [10], [11].…”

mentioning

confidence: 99%

Lattice-Based Cryptography and Fog Computing Based Efficient Anonymous Authentication Scheme for 5G-Assisted Vehicular Communications

Al-Mekhlafi,

Al-Janabi,

Khalil

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Vehicular fog systems that are enabled by fifth-generation (5G) networks can significantly improve traffic safety and efficiency through vehicle-to-vehicle communication. Vehicles must have their legal status verified before they can join the network, as vehicular systems depend on open communication. Consequently, several anonymous authentication schemes have been created to withstand malicious vehicles, with the foundations being bilinear pairing or elliptic curve cryptography. But quantum attacks can easily defeat these schemes. To address this problem, this study introduces a 5G-supported vehicular fog system anonymous authentication strategy that makes use of lattice-based cryptography. The suggested system communicates with trusted authorities (TAs) and automobiles over the 5G-base station's communication range, and it employs fog servers to authenticate vehicles and distribute anonymous data. By recognizing the cars and the users they are affiliated with, the TA in the suggested method can keep tabs on everyone working on a specific task. With the use of ProVerif, a protocol verification tool, we were able to determine that our authentication mechanism effectively hides user, vehicle, and fog server data. After calculating the associated computation and transmission costs, we integrated the suggested technique with state-of-the-art anonymous authentication utilizing lattice-based encryption to ward off quantum attacks. The computational costs of the proposal technique for message signing and batch/single verification are 0.3149 ms, 0.0724 ms, and 0.0724 n ms, respectively. Whereas, 18448 bits is the communication cost of the suggested method. Thus, the results show that our solution has a reduced processing cost for creating and verifying message signatures, but a much higher transmission cost.

show abstract

Collaborative Learning Based Sybil Attack Detection in Vehicular AD-HOC Networks (VANETS)

Cited by 26 publications

References 41 publications

Privacy and security issues surrounding vehicular Adhoc networks

Privacy and security issues surrounding vehicular Adhoc networks

Ensemble Learning Based Malicious Node Detection in SDN-Based VANETs

Lattice-Based Cryptography and Fog Computing Based Efficient Anonymous Authentication Scheme for 5G-Assisted Vehicular Communications

Contact Info

Product

Resources

About