VANET: Trust Evaluation Using Artificial Neural Network

Mahalakshmi, G. S.; E, Uma; Vinitha, M; Aroosiya, M

doi:10.3233/apc210117

Cited by 2 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML can be used to develop effective trust and reputation mechanisms that can help maintain the integrity of network communications. By using Artificial Neural Networks (ANNs), decision trees, Bayesian networks, reinforcement learning, and game theory, it is possible to identify trustworthy nodes and flag potentially malicious nodes, improving the overall security and reliability of WSNs [14,16,36,53,56,57].…”

Section: Trust and Reputation Systemsmentioning

confidence: 99%

A Review of Security Challenges and Solutions in Wireless Sensor Networks

Hassan,

Madkour,

Nouh

2023

Journal of Al-Azhar University Engineering Sector

View full text Add to dashboard Cite

Wireless Sensor Networks (WSNs) are a vital component of the Internet of Things (IoT) since it is a viable technology for a variety of real-time applications. This is mainly because WSNs are naturally distributed, low-cost, fault-tolerant, self-organizing, easily deployable, scalable, and function without a predefined infrastructure. Their applications include surveillance, smart power grids, traffic networks, telecommunications systems, smart cities, intelligent transportation, industrial quality control, and the military, to mention a few. However, the security of WSNs is a major concern due to their vulnerability to various types of attacks, including node compromise, eavesdropping, and denial-of-service. This paper covers the security issues in WSNs and discusses the security challenges faced by these networks and the existing solutions. It illustrates the possible attacks and explores the different security mechanisms that can be used to protect WSNs, including encryption, authentication, and key management. Trust and reputation management are presented being effective techniques for mitigating routing attacks, and the role of machine learning techniques in enhancing WSN security is outlined. The paper concludes by discussing future research directions in WSN security. The findings of this paper are valuable for researchers, network administrators, and policymakers who are involved in the design and implementation of secure WSNs.

show abstract

Section: Trust and Reputation Systemsmentioning

confidence: 99%

A Review of Security Challenges and Solutions in Wireless Sensor Networks

Hassan,

Madkour,

Nouh

2023

Journal of Al-Azhar University Engineering Sector

View full text Add to dashboard Cite

show abstract

“…The backpropagation algorithm is used to train an ANN in a supervised mode by updating the network weights many times iteratively to get an accurate prediction of the target RCF. Each iteration involves two phases: forward calculation and error backpropagation [13,43,52]. Algorithm 1 shows the training steps.…”

Section: The Ann Training Processmentioning

confidence: 99%

A Realtime Adaptive Trust Model Based on Artificial Neural Networks for Wireless Sensor Networks

Hassan

Madkour

Nouh

2023

JCSANDM

View full text Add to dashboard Cite

Wireless sensor networks (WSNs) are vulnerable to security attacks due to the unbounded nature of the wireless medium, restricted node resources, and cooperative routing. Standard cryptography and authentication mechanisms help protect against external attacks, but a compromised node can easily bypass them. This work aims to protect WSNs against internal attacks, which are mostly launched from compromised nodes to disrupt the network’s operation and/or reduce its performance. The trust and reputation management framework provides a routing cost function for selecting the best secure next hop. Tuning the trust weights is essential to cope with the constant changes in the network environment, such as the sensor nodes’ behaviours and locations. To allow real-time operation, the proposed framework introduces an artificial neural network (ANN) in each sensor node that automatically adjusts the weights of the considered trust metrics according to the WSN state. A large dataset is generated to train and test the ANN using a multitude of simulated cases. A prototype is developed and tested using the J-Sim simulator to show the performance gain resulting from applying the adaptive trust model. The experimental results showed that the adaptive model has robust performance and has achieved an improved packet delivery ratio with reduced power consumption and reduced average packet loss. The results showed that when sensor nodes were static and malicious nodes were present, the average accuracy was 99.6%, while when they were in motion, it was 88.1%.

show abstract

VANET: Trust Evaluation Using Artificial Neural Network

Cited by 2 publications

References 8 publications

A Review of Security Challenges and Solutions in Wireless Sensor Networks

A Review of Security Challenges and Solutions in Wireless Sensor Networks

A Realtime Adaptive Trust Model Based on Artificial Neural Networks for Wireless Sensor Networks

Contact Info

Product

Resources

About