Authors:
Mohammad Ahmad, S. Sajini, P. Mahendran, M. Sakthivanitha, M. Mohamed Sirajudeen

Addresses:
School of Computer Science and Technology, University of Bedfordshire, Luton, England, United Kingdom. Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Information Technology, Vels Institute of Science Technology and Advanced Studies, Chennai, Tamil Nadu, India. School of Computer Science and Emerging Technologies, Nilgiri College of Arts and Science, The Nilgiris, Tamil Nadu, India.

Abstract:

Vehicular Ad Hoc Networks are one of the key components to be developed for intelligent transportation systems, capable of creating real-time communication between vehicles and roadside infrastructure. However, it is very challenging to ensure secure communication in the networks mentioned above, especially given their dynamic and decentralised nature. In this paper, the authors present DL-SCIV (Deep Learning-Based Secure Communication Initialisation in VANETs) for enhanced security and reliability. Core to the scheme is the collection and preprocessing of data from vehicle sensors and communication history, feature extraction, and training deep learning models such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The models are used for the aforementioned contribution, which offers significant benefits, including security, scalability, and real-time continuous monitoring and anomaly detection to mitigate potential threats by ensuring a sophisticated approach to security problems. The processing capabilities. These include data privacy issues, model complexity, and the necessity to accommodate evolving threats. Researchers propose a deep learning-based authentication scheme that provides a high-level security framework for communication in VANETs, supporting the development of an intelligent travel system.

Keywords: VANET and CNN; Deep Learning; Authentication Scheme; Secure Communication; Intelligent Transportation Systems; Anomaly Detection; Traffic Management; Roadside Infrastructure.

Received on: 14/08/2025, Revised on: 03/10/2025, Accepted on: 08/12/2025, Published on: 31/03/2026

DOI: 10.69888/FTSCIS.2026.000711

FMDB Transactions on Sustainable Critical Infrastructures, 2026 Vol. 1 No. 1, Pages: 33-44

• Views : 14
• Downloads : 5

Download PDF