The increasing connectivity of in-vehicle electronic control systems has intensified the need for robust cybersecurity solutions, especially for the Controller Area Network (CAN) bus. This study proposes a deep learning–based Intrusion Detection System (IDS) utilizing a Generative Adversarial Network (GAN) architecture to detect anomalous CAN bus traffic in real time. The GAN model is trained solely on legitimate CAN messages, enabling it to learn the underlying statistical patterns of normal communication without relying on predefined attack signatures. The proposed GAN-IDS demonstrates strong detection performance, achieving an accuracy of 98.7% and an F1-Score of 98.5%, outperforming conventional deep learning baselines. To assess deployment feasibility, the discriminator is optimized using TensorFlow Lite (TFLite) and deployed on a Raspberry Pi 4 integrated with a PiCAN2 interface. Hardware evaluation confirms real-time operation with a low detection latency of 2.9 milliseconds per message sequence. System interpretability is further enhanced through SHapley Additive exPlanations (SHAP), which identify CAN ID, engine torque, and RPM as the most influential features contributing to anomaly classification. The proposed GAN-based IDS offer a scalable, manufacturer-independent, and non-intrusive cybersecurity solution for modern Electric Vehicles. Its combination of high detection performance, real-time hardware deployment, and interpretable decision-making marks a significant step toward more intelligent and resilient security mechanisms for future connected and autonomous vehicles.
| Published in | American Journal of Information Science and Technology (Volume 9, Issue 4) |
| DOI | 10.11648/j.ajist.20250904.16 |
| Page(s) | 304-323 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
CAN Bus Security, Generative Adversarial Networks, Intrusion Detection System, Electric Vehicles, Real-time Anomaly Detection
| [1] | Hoppe, T., S. Kiltz, and J. Dittmann. 2011. “Security Threats to Automotive CAN Networks — Practical Examples and Selected Short-Term Countermeasures.” Reliability Engineering & System Safety 96(1): 11–25. |
| [2] | Müter, G., and J. Asaj. 2011. “Entropy-Based Anomaly Detection for In-Vehicle Networks.” Proceedings of the 2011 IEEE Intelligent Vehicles Symposium. |
| [3] | Song, H. M., H. R. Kim, and H. K. Kim. 2016. “Intrusion Detection System Based on the Analysis of Time Intervals of CAN Messages for In-Vehicle Network.” Proceedings of ICOIN 2016. |
| [4] | Marchetti, M., and D. Stabili. 2017. “Anomaly Detection of CAN Bus Messages through Analysis of ID Sequences.” Proceedings of the 2017 IEEE Intelligent Vehicles Symposium (IV). |
| [5] | Choi, W., K. Joo, H. J. Jo, M. C. Park, and D. H. Lee. 2018. “VoltageIDS: Low-Level Communication Characteristics for Automotive Intrusion Detection System.” IEEE Transactions on Information Forensics and Security 13(8): 2114–2129. |
| [6] | Groza, B., and P.-S. Murvay. 2019. “Efficient Intrusion Detection with Bloom Filtering in Controller Area Networks.” IEEE Transactions on Information Forensics and Security 14(4): 1037–1051. |
| [7] | Wu, W., et al. 2018. “Sliding Window Optimized Information Entropy Analysis Method for Intrusion Detection on In-Vehicle Networks.” IEEE Access. |
| [8] | Kang, M.-J., and J.-W. Kang. 2016. “Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security.” PLOS ONE 11(6): e0155781. |
| [9] | Seo, E., H. M. Song, and H. K. Kim. 2019. “GIDS: GAN-based Intrusion Detection System for In-Vehicle Network.” arXiv preprint / technical report. |
| [10] | Zhang, G., Q. Liu, C. Cao, J. Li, and Y. Li. 2023. “Bit Scanner: Anomaly Detection for In-Vehicle CAN Bus Using Binary Sequence Whitelisting.” Computers & Security (2023): Article 103436. |
| [11] | Xia, X., X. Pan, N. Li, X. He, L. Ma, X. Zhang, and N. Ding. 2022. “GAN-based Anomaly Detection: A Review.” Neurocomputing 493: 497–535. |
| [12] | Creswell, A., T. White, V. Dumoulin, K. Arulkumaran, B. Sengupta, and A. A. Bharath. 2017. “Generative Adversarial Networks: An Overview.” IEEE Signal Processing Magazine 35(1): 53–65. |
| [13] | Groza, B., P.-S. Murvay, A. van Herrewege, and I. Verbauwhede. 2012. “LiBrA-CAN: A Lightweight Broadcast Authentication Protocol for Controller Area Networks.” In Lecture Notes in Computer Science (CANS 2012), 185–200. |
| [14] | Wei, P., and B. Wang. 2022. “A Novel Intrusion Detection Model for the CAN Bus Packet of In-Vehicle Network Based on Attention Mechanism and Autoencoder.” Digital Communications and Networks 9(2). |
| [15] | Feng, Yitong, and Ming Zhao. 2023. “Transformer-Based Temporal Modeling for In-Vehicle CAN Intrusion Detection.” IEEE Transactions on Intelligent Transportation Systems 24(9): 11245–11257. |
| [16] | Bai, Rong, Wenqian Shi, and Jia Li. 2023. “Conditional GAN Framework for Anomaly Synthesis in Automotive CAN Networks.” Proceedings of the ACM Conference on Security of Connected Vehicles, 55–66. |
| [17] | Ren, Xuechen, and Lei Zhang. 2024. “Cycle-Consistent Adversarial Modeling for Unsupervised CAN Bus Intrusion Detection.” IEEE Transactions on Dependable and Secure Computing. |
| [18] | Kim, Sungmin, and Hyun-Woo Lee. 2023. “Contrastive Learning–Enhanced Autoencoder for Robust CAN Bus Anomaly Detection.” IEEE Access 11: 145320–145334. |
| [19] | Huang, Lin, Wei Chen, and Xiaoqiang Chen. 2024. “Graph Neural Network Modeling of CAN Identifier Relationships for Intrusion Detection.” Information Sciences 665: 120345. |
| [20] | Martínez, Diego, Silvia Torres, and Julian Pérez. 2023. “Uncertainty-Aware Detection of CAN Anomalies Using Variational Inference.” Expert Systems with Applications 223: 120567. |
| [21] | Liu, Qiang, and Hao Sun. 2023. “Multi-View Learning for Comprehensive CAN Bus Intrusion Detection.” Engineering Applications of Artificial Intelligence 125: 107204. |
| [22] | Wang, Rui, and Fang Li. 2024. “Hierarchical Feature Fusion for Cross-Vehicle Generalizable CAN Intrusion Detection.” Journal of Network and Computer Applications 235: 103642. |
APA Style
Kalyan, B. K. P., Chandana, M. S., Karimalla, N., Bukaita, W. (2025). Generative Adversarial Network–based Intrusion Detection for Securing In-vehicle Communication in Electric Vehicles. American Journal of Information Science and Technology, 9(4), 304-323. https://doi.org/10.11648/j.ajist.20250904.16
ACS Style
Kalyan, B. K. P.; Chandana, M. S.; Karimalla, N.; Bukaita, W. Generative Adversarial Network–based Intrusion Detection for Securing In-vehicle Communication in Electric Vehicles. Am. J. Inf. Sci. Technol. 2025, 9(4), 304-323. doi: 10.11648/j.ajist.20250904.16
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajist.20250904.16,
author = {Bogineni Kasi Pavan Kalyan and Mergu Siri Chandana and Navya Karimalla and Wisam Bukaita},
title = {Generative Adversarial Network–based Intrusion Detection for Securing In-vehicle Communication in Electric Vehicles},
journal = {American Journal of Information Science and Technology},
volume = {9},
number = {4},
pages = {304-323},
doi = {10.11648/j.ajist.20250904.16},
url = {https://doi.org/10.11648/j.ajist.20250904.16},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajist.20250904.16},
abstract = {The increasing connectivity of in-vehicle electronic control systems has intensified the need for robust cybersecurity solutions, especially for the Controller Area Network (CAN) bus. This study proposes a deep learning–based Intrusion Detection System (IDS) utilizing a Generative Adversarial Network (GAN) architecture to detect anomalous CAN bus traffic in real time. The GAN model is trained solely on legitimate CAN messages, enabling it to learn the underlying statistical patterns of normal communication without relying on predefined attack signatures. The proposed GAN-IDS demonstrates strong detection performance, achieving an accuracy of 98.7% and an F1-Score of 98.5%, outperforming conventional deep learning baselines. To assess deployment feasibility, the discriminator is optimized using TensorFlow Lite (TFLite) and deployed on a Raspberry Pi 4 integrated with a PiCAN2 interface. Hardware evaluation confirms real-time operation with a low detection latency of 2.9 milliseconds per message sequence. System interpretability is further enhanced through SHapley Additive exPlanations (SHAP), which identify CAN ID, engine torque, and RPM as the most influential features contributing to anomaly classification. The proposed GAN-based IDS offer a scalable, manufacturer-independent, and non-intrusive cybersecurity solution for modern Electric Vehicles. Its combination of high detection performance, real-time hardware deployment, and interpretable decision-making marks a significant step toward more intelligent and resilient security mechanisms for future connected and autonomous vehicles.},
year = {2025}
}
TY - JOUR T1 - Generative Adversarial Network–based Intrusion Detection for Securing In-vehicle Communication in Electric Vehicles AU - Bogineni Kasi Pavan Kalyan AU - Mergu Siri Chandana AU - Navya Karimalla AU - Wisam Bukaita Y1 - 2025/12/20 PY - 2025 N1 - https://doi.org/10.11648/j.ajist.20250904.16 DO - 10.11648/j.ajist.20250904.16 T2 - American Journal of Information Science and Technology JF - American Journal of Information Science and Technology JO - American Journal of Information Science and Technology SP - 304 EP - 323 PB - Science Publishing Group SN - 2640-0588 UR - https://doi.org/10.11648/j.ajist.20250904.16 AB - The increasing connectivity of in-vehicle electronic control systems has intensified the need for robust cybersecurity solutions, especially for the Controller Area Network (CAN) bus. This study proposes a deep learning–based Intrusion Detection System (IDS) utilizing a Generative Adversarial Network (GAN) architecture to detect anomalous CAN bus traffic in real time. The GAN model is trained solely on legitimate CAN messages, enabling it to learn the underlying statistical patterns of normal communication without relying on predefined attack signatures. The proposed GAN-IDS demonstrates strong detection performance, achieving an accuracy of 98.7% and an F1-Score of 98.5%, outperforming conventional deep learning baselines. To assess deployment feasibility, the discriminator is optimized using TensorFlow Lite (TFLite) and deployed on a Raspberry Pi 4 integrated with a PiCAN2 interface. Hardware evaluation confirms real-time operation with a low detection latency of 2.9 milliseconds per message sequence. System interpretability is further enhanced through SHapley Additive exPlanations (SHAP), which identify CAN ID, engine torque, and RPM as the most influential features contributing to anomaly classification. The proposed GAN-based IDS offer a scalable, manufacturer-independent, and non-intrusive cybersecurity solution for modern Electric Vehicles. Its combination of high detection performance, real-time hardware deployment, and interpretable decision-making marks a significant step toward more intelligent and resilient security mechanisms for future connected and autonomous vehicles. VL - 9 IS - 4 ER -
Math and Computer Science Department, Lawrence Technological University, South Field, USA
Math and Computer Science Department, Lawrence Technological University, South Field, USA
Math and Computer Science Department, Lawrence Technological University, South Field, USA
Math and Computer Science Department, Lawrence Technological University, South Field, USA
Information