Paper Titles
Artificial Intelligence in Gas Operations: Emerging Trends and New Frontiers in Exploration and Production
p.75
Mobile-Optimised Deep Learning Architecture for Multi-Crop Disease Detection Using CNN and SVM
p.87
Mirai Botnet DDoS Attack Simulation Using Build Your Own Botnet (BYOB)
p.101
Empirical Data from the Case Study on the State of the Art of Cybercrime in Nigeria
p.113
An EfficientNet-Based Framework for Real-Time and Reliable Intrusion Detection in Vehicular Networks
p.135
Optimized Malware Detection Framework Using Principal Components Analysis
p.147
Investigating the Efficacy of Deep Learning Techniques in Detecting Advanced Persistent Threats (APTs)
p.163
Virtual Reality for Mechanical and Mechatronic Engineering Education in Africa: A Review of Applications and Future Prospects
p.181
Enhancing Language Acquisition for Beginners: A Data-Driven Approach
p.201

An EfficientNet-Based Framework for Real-Time and Reliable Intrusion Detection in Vehicular Networks

Article Preview

Abstract:

The Internet of Vehicles (IoV) has transformed transportation through seamless communication and intelligent coordination among connected vehicles. This advancement, however, has introduced a broader spectrum of cyber risks, necessitating intelligent and efficient threat detection strategies. This paper introduces a lightweight intrusion detection framework tailored for connected vehicle ecosystems, employing EfficientNet for deep feature extraction and a Particle Swarm Optimization (PSO)-tuned Random Forest (RF) classifier for classification. Transfer learning was utilized to enhance feature compactness and relevance, while PSO refined the RF parameters to maximize detection accuracy. Experimental validation on two publicly available benchmark datasets demonstrated superior performance, achieving perfect classification on the Car-Hacking dataset and 99.89% accuracy on CICIDS2017. The model also sustained high levels of detection precision, sensitivity, and F1 measure across multiple intrusion categories. With an inference latency of just 0.0173 milliseconds per sample, the system processes over 57,000 flows per second—confirming its viability for deployment in real-time, resource-limited vehicular environments.

You might also be interested in these eBooks
The 3rd International Conference of Multidisciplinary Engineering and Applied Sciences (ICMEAS): Selected papers in advanced engineering View Preview

Info:

Periodical:

Engineering Headway (Volume 37)

Pages:

135-145

DOI:

https://doi.org/10.4028/p-c06A2r

Citation:

Cite this paper

Online since:

March 2026

Authors:

Idris Shehu Musa*, Muhammed Bashir Mu'azu, Yusuf Ibrahim

Keywords:

Connected Vehicle Networks, Deep Feature Representation, EfficientNet, IoV Threat Detection, Low-Latency Monitoring, Particle Swarm Optimization, Rf Ensemble Classifier, Transfer Learning Techniques

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2026 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] M. N. O. Sadiku, M. Tembely, and S. M. Musa, "Internet of Vehicles: An Introduction," Int. J. Adv. Res. Comput. Sci. Softw. Eng., vol. 8, no. 1, p.11–15, 2018.

Google Scholar

[2] A. Haddaji, S. Ayed, and L. C. Fourati, "A novel and efficient framework for in-vehicle security enforcement," Ad Hoc Netw., vol. 158, 2024, Art. no. 103093.

DOI: 10.1016/j.adhoc.2024.103481

Google Scholar

[3] K. Jin, D. Xu, Q. Xiang, and X. Li, "MAPPS: A lightweight and precise malware detection system for in-vehicle networks," Internet of Things, vol. 15, 2021, Art. no. 100422.

Google Scholar

[4] Upstream Security, "2023 Global Automotive Cybersecurity Report," 2023. [Online]. Available: https://upstream.auto/resources/global-automotive-cybersecurity-report-2023/ [Accessed: Mar. 15, 2024].

Google Scholar

[5] K. Huang, R. Xian, M. Xian, H. Wang, and L. Ni, "A comprehensive intrusion detection method for the Internet of Vehicles based on federated learning architecture," Comput. Secur., vol. 147, 2024, Art. no. 103581.

DOI: 10.1016/j.cose.2024.104067

Google Scholar

[6] H. Bangui, M. Ge, and B. Buhnova, "A hybrid data-driven model for intrusion detection in VANET," Proc. Comput. Sci., vol. 184, p.516–523, 2021.

DOI: 10.1016/j.procs.2021.03.065

Google Scholar

[7] S. T. Banafshehvaragh and A. M. Rahmani, "Intrusion, anomaly, and attack detection in smart vehicles," Microprocess. Microsyst., vol. 96, 2023, Art. no. 104365.

DOI: 10.1016/j.micpro.2022.104726

Google Scholar

[8] A. Alhowaide, I. Alsmadi, and J. Tang, "Ensemble Detection Model for IoT IDS," Internet Things, vol. 16, 2021, Art. no. 100472.

DOI: 10.1016/j.iot.2021.100435

Google Scholar

[9] A. R. Gad, A. A. Nashat, and T. M. Barkat, "Intrusion Detection System Using Machine Learning for Vehicular Ad Hoc Networks Based on ToN-IoT Dataset," IEEE Access, vol. 9, p.142206–142217, 2021.

DOI: 10.1109/access.2021.3120626

Google Scholar

[10] A. Halbouni, T. S. Gunawan, M. H. Habaebi, M. Halbouni, M. Kartiwi, and R. Ahmad, "CNN-LSTM: Hybrid Deep Neural Network for Network Intrusion Detection System," IEEE Access, vol. 10, p.99837–99849, 2022.

DOI: 10.1109/access.2022.3206425

Google Scholar

[11] T. Alladi, V. Kohli, V. Chamola, and F. R. Yu, "A deep learning based misbehavior classification scheme for intrusion detection in cooperative intelligent transportation systems," Digit. Commun. Netw., vol. 9, no. 5, p.1113–1122, 2023.

DOI: 10.1016/j.dcan.2022.06.018

Google Scholar

[12] H. C. Lin, P. Wang, K. M. Chao, W. H. Lin, and J. H. Chen, "Using Deep Learning Networks to Identify Cyber Attacks on Intrusion Detection for In-Vehicle Networks," Electronics, vol. 11, no. 14, 2022, Art. no. 2123.

DOI: 10.3390/electronics11142180

Google Scholar

[13] Y. Wang, G. Qin, M. Zou, Y. Liang, G. Wang, K. Wang, Y. Feng, and Z. Zhang, "A lightweight intrusion detection system for internet of vehicles based on transfer learning and MobileNetV2 with hyper-parameter optimization," Multimedia Tools Appl., vol. 83, no. 8, p.22347–22369, 2024.

DOI: 10.1007/s11042-023-15771-6

Google Scholar

[14] L. Yang and A. Shami, "A Transfer Learning and Optimized CNN Based Intrusion Detection System for Internet of Vehicles," in Proc. IEEE Int. Conf. Commun. (ICC), Seoul, Korea, 2022, pp.2774-2779.

DOI: 10.1109/icc45855.2022.9838780

Google Scholar

[15] X. Li, Y. Yan, J. Cui, K. Lu, and Z. Lu, "IDBV: A Transfer Learning-Based Approach for Keeping Intrusion Detection Models Up-to-Date in Vehicular Networks," IEEE Internet Things J., vol. 8, no. 3, p.1577–1589, 2021.

Google Scholar

[16] F. Jin, M. Chen, W. Zhang, Y. Yuan, and S. Wang, "Intrusion detection on internet of vehicles via combining log-ratio oversampling, outlier detection and metric learning," Inf. Sci., vol. 579, p.814–831, 2021.

DOI: 10.1016/j.ins.2021.08.010

Google Scholar

[17] M. Han, P. Cheng, and S. Ma, "PPM-InVIDS: Privacy protection model for in-vehicle intrusion detection system based complex-valued neural network," Veh. Commun., vol. 31, 2021, Art. no. 100347.

DOI: 10.1016/j.vehcom.2021.100374

Google Scholar

[18] A. K. Desta, S. Ohira, I. Arai, and K. Fujikawa, "Rec-CNN: In-vehicle networks intrusion detection using convolutional neural networks trained on recurrence plots," Veh. Commun., vol. 35, 2022, Art. no. 100471.

DOI: 10.1016/j.vehcom.2022.100470

Google Scholar

[19] N. Khatri, S. Lee, and S. Y. Nam, "Transfer Learning-Based Intrusion Detection System for a Controller Area Network," IEEE Access, vol. 11, p.120963–120982, 2023.

DOI: 10.1109/access.2023.3328182

Google Scholar

[20] A. Manderna, S. Kumar, U. Dohare, M. Aljaidi, O. Kaiwartya, and J. Lloret, "Vehicular Network Intrusion Detection Using a Cascaded Deep Learning Approach with Multi-Variant Metaheuristic," Sensors, vol. 23, no. 21, 2023, Art. no. 8826.

DOI: 10.3390/s23218772

Google Scholar

[21] M. H. Khan, A. R. Javed, Z. Iqbal, M. Asim, and A. I. Awad, "DivaCAN: Detecting in-vehicle intrusion attacks on a controller area network using ensemble learning," Comput. Secur., vol. 139, 2024, Art. no. 103697.

DOI: 10.1016/j.cose.2024.103712

Google Scholar

[22] A. Khalil, H. Farman, M. M. Nasralla, B. Jan, and J. Ahmad, "Artificial Intelligence-based intrusion detection system for V2V communication in vehicular adhoc networks," Ain Shams Eng. J., vol. 15, no. 4, 2024, Art. no. 102402.

DOI: 10.1016/j.asej.2023.102616

Google Scholar

[23] M. S. Korium, M. Saber, A. Beattie, A. Narayanan, S. Sahoo, and P. H. J. Nardelli, "Intrusion detection system for cyberattacks in the Internet of Vehicles environment," Ad Hoc Netw., vol. 153, 2024, Art. no. 103203.

DOI: 10.1016/j.adhoc.2023.103330

Google Scholar

[24] E. C. P. Neto, H. Taslimasa, S. Dadkhah, S. Iqbal, P. Xiong, T. Rahman, and A. A. Ghorbani, "CICIoV2024: Advancing realistic IDS approaches against DoS and spoofing attack in IoV CAN bus," Internet of Things, vol. 26, 2024, Art. no. 100823.

DOI: 10.1016/j.iot.2024.101209

Google Scholar

[25] N. Ahmed, F. Hassan, K. Aurangzeb, A. H. Magsi, and M. Alhussein, "Advanced machine learning approach for DoS attack resilience in internet of vehicles security," Heliyon, vol. 10, no. 8, 2024, Art. no. e24935.

DOI: 10.1016/j.heliyon.2024.e28844

Google Scholar

[26] S. Wang, Y. Wang, B. Zheng, J. Cheng, Y. Su, and Y. Dai, "Intrusion Detection System for Vehicular Networks Based on MobileNetV3," IEEE Access, vol. 12, p.106285–106302, 2024.

DOI: 10.1109/access.2024.3437416

Google Scholar

[27] C. Fan, J. Cui, H. Jin, H. Zhong, I. Bolodurina, and D. He, "Auto-Updating Intrusion Detection System for Vehicular Network: A Deep Learning Approach Based on Cloud-Edge-Vehicle Collaboration," IEEE Trans. Veh. Technol., vol. 73, no. 5, pp.6269-6283, 2024.

DOI: 10.1109/tvt.2024.3399219

Google Scholar

[28] Y. Shi and R. Eberhart, "A modified particle swarm optimizer," in Proc. IEEE Int. Conf. Evol. Comput., Anchorage, AK, USA, 1998, p.69–73.

Google Scholar