Improved Recurrent Neural Network Schema for Validating Digital Signatures in VANET

Abstract

Vehicular ad hoc networks (VANETs) allow communication between stationary or moving vehicles with the assistance of wireless technology. Among various existing issues in smart VANETs, secure communication is the key challenge in VANETs with a 5G network. Smart vehicles must communicate with a broad range of advanced road systems including traffic control and smart payment systems. Many security mechanisms are used in VANETs to ensure safe transmission; one such mechanism is cryptographic digital signatures based on public key infrastructure (PKI). In this mechanism, secret private keys are used for digital signatures to validate the identity of the message along with the sender. However, the validation of the digital signatures in fast-moving vehicles is extremely difficult. Based on an improved perceptron model of an artificial neural network (ANN), this paper proposes an efficient technique for digital signature verification. Still, manual signatures are extensively used for authentication across the world. However, manual signatures are still not employed for security in automotive and mobile networks. The process of converting manual signatures to pseudo-digital-signatures was simulated using the improved Elman backpropagation (I-EBP) model. A digital signature was employed during network connection to authenticate the legitimacy of the sender’s communications. Because it contained information about the vehicle on the road, there was scope for improvement in protecting the data from attackers. Compared to existing schemes, the proposed technique achieved significant gains in computational overhead, aggregate verification delay, and aggregate signature size.

An opportunistic energy‐efficient dynamic self‐configuration clustering algorithm in WSN‐based IoT networks

“…The parameters determining the CHs are node mobility, node location, and the node's average residual energy (ARE). 11 For the duration of the sequence of operations, the selected CH remains the head. Clustering methods are classified into two types: those with a fixed cluster size and those with a variable cluster size.…”

“…The CHs are chosen based on the node parameters. The parameters determining the CHs are node mobility, node location, and the node's average residual energy (ARE) 11 . For the duration of the sequence of operations, the selected CH remains the head.…”

Digital Identity Verification: Transforming KYC Processes in Banking Through Advanced Technology and Enhanced Security Measures

“…Even with advanced technologies like blockchain, security remains a paramount concern. Arpit Jain and his team's research on vehicular ad hoc networks (VANETs) highlights the challenges of validating digital signatures in fast-moving scenarios [12]. While the study primarily focuses on VANETs, the concerns raised about the validation of digital signatures are relevant to the banking sector, especially in high-frequency trading environments.…”

An enhanced self-learning-based clustering scheme for real-time traffic data distribution in wireless networks

“…A detailed description of the network traffic analysis is as follows: Datasets: Testing and assessing are the essential tasks of network traffic analysis for detecting the flow of traffic data. A standard Center for Applied Internet Data Analysis (CAIDA) [10] dataset is employed for computing the network traffic analysis for various network applications [11] . Preprocessing: Preprocessing is applied as the second phase for changing the real-world data into a reasonable format.…”

“…Datasets: Testing and assessing are the essential tasks of network traffic analysis for detecting the flow of traffic data. A standard Center for Applied Internet Data Analysis (CAIDA) [10] dataset is employed for computing the network traffic analysis for various network applications [11] .…”