Hybrid Dilated and Attention-Based Framework for Effective Detection of Cybersecurity Spoofing in Vehicular Networks

Vishal Ramdas Deshmukh; Monika Tripathi

doi:10.36948/ijfmr.2025.v07i06.62655

Hybrid Dilated and Attention-Based Framework for Effective Detection of Cybersecurity Spoofing in Vehicular Networks

Author(s)	Mr. Vishal Ramdas Deshmukh, Prof. Dr. Monika Tripathi
Country	India
Abstract	The need for constant data transmission among Electronic Control Units (ECUs) in the automotive environment has grown due to the quick development of linked and autonomous vehicle technologies. Despite being widely utilized due to its dependability and real-time communication capabilities, the Controller Area Network (CAN bus) is extremely vulnerable to spoofing attacks due to its lack of built-in security mechanisms. These assaults provide significant safety issues, allow adversaries to introduce fake messages, and interfere with regular ECU functions. CAN security has benefited greatly from existing intrusion detection techniques, such as entropy-based analysis, statistical detection, RNN/LSTM systems, reinforcement learning, and physical-layer authentication. Nevertheless, many of these techniques still have shortcomings, including computational overhead, sensitivity to noise, overfitting, slow training, scalability issues, and decreased accuracy in complex attack scenarios. To overcome these limitations, this research proposes an efficient cybersecurity spoofing attack detection framework for vehicular networks using a Hybridized Dilated and Attention-based Network (HD-AN). The framework incorporates a structured pipeline consisting of data preprocessing, weighted feature extraction through Restricted Boltzmann Machine (RBM), and optimization of feature weights using the Improved Coronavirus Mask Protection Algorithm (ICMPA). The optimized features are then processed through the HD-AN model, which combines dilated temporal convolutions with attention mechanisms and residual LSTM modules to capture long-range temporal dependencies in CAN traffic. This architecture enhances robustness, improves feature discrimination, and enables early detection of malicious patterns. The proposed framework is expected to outperform classical and state-of-the-art methods based on accuracy, precision, sensitivity, specificity, F1-score, MCC, and error-based metrics such as FPR, FNR, and FDR, thereby providing a reliable and computationally efficient defense mechanism for real-time vehicular cybersecurity.
Keywords	Vehicular Networks; CAN Bus Security; Spoofing Attack Detection; Cybersecurity; Intrusion Detection System (IDS); Hybrid Dilated Convolution; Attention Mechanism; Residual LSTM; Restricted Boltzmann Machine (RBM); ICMPA Optimization; Deep Learning; Connected and Autonomous Vehicles (CAVs).
Field	Engineering
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-12-06
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.62655

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 3 Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Hybrid Dilated and Attention-Based Framework for Effective Detection of Cybersecurity Spoofing in Vehicular Networks

Share this