AI-Powered Data Privacy and Threat Detection in Autonomous and Connected Vehicles for Smart City Ecosystems

International Journal of Electrical and Electronics Engineering

© 2026 by SSRG - IJEEE Journal

Volume 13 Issue 3

Year of Publication : 2026

Authors : Ajith A S, Gaurav Gadge, Archana S. Ubale, Aarti Raman Sonawane

10.14445/23488379/IJEEE-V13I3P109

How to Cite?

Ajith A S, Gaurav Gadge, Archana S. Ubale, Aarti Raman Sonawane, "AI-Powered Data Privacy and Threat Detection in Autonomous and Connected Vehicles for Smart City Ecosystems," SSRG International Journal of Electrical and Electronics Engineering, vol. 13,  no. 3, pp. 113-124, 2026. Crossref, https://doi.org/10.14445/23488379/IJEEE-V13I3P109

Abstract:

Intelligent sensing and communication systems are increasingly used in autonomous and connected vehicles, which present new challenges in data privacy and cyber-threat detection in smart city environments. This work proposes an AI-driven multimodal security framework that integrates sensor fusion, edge-cloud coordination, federated learning, and adversarial robustness for reliable and privacy-preserving threat detection. The proposed methodology integrates multimodal feature embedding, secure aggregation of parameters, hybrid anomaly scoring, and adaptive decision flow across the edge-cloud layers. Experimental results demonstrate promising performance with 97.8% detection accuracy, 96.9% F1-score, 93.6% robustness, and 98.3% privacy preservation, showing very stable results in all scenarios, such as urban, highway, nighttime, and noisy weather. Performance comparison does present palpable gains over state-of-the-art IDS and the existing federated model. This work is thus concluded with the belief that distributed intelligence integrated with resilient multi-model analytics significantly strengthens vehicular security with a scalable and future-ready solution for smart city ecosystems.

Keywords:

Autonomous Vehicles, Threat Detection, Federated Learning, Multimodal Fusion, Smart City Security.

References:

[1] Sidi Lu, and Weisong Shi, Introduction to Vehicle Computing, Vehicle Computing, pp. 1-24, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Santosh Gore et al., “A Machine Learning-based Detection of IoT Cyberattacks in Smart City Application,” Lecture Notes in Networks and Systems, pp. 73-81, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Eslam Farsimadan, Leila Moradi, and Francesco Palmieri, “A Review on Security Challenges in V2X Communications Technology for VANETs,” IEEE Access, vol. 13, pp. 31069-31094, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Deepak Kumar et al., “Trustworthy IoT Infrastructures: Privacy-Preserving Federated Learning with Efficient Secure Aggregation for Cybersecurity,” 2024 International Conference on Integrated Intelligence and Communication Systems (ICIICS), Kalaburagi, India, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Fayez Alanazi, “AI on the Road-A Review of Technologies Enhancing Urban Traffic Safety and Efficiency,” Promet-Traffic & Transportation, vol. 37, no. 5, pp. 1179-1203, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Pradeep Gupta et al., “Hybrid Convolutional Neural Network and Generative Adversarial Network Framework for Robust Deepfake Detection: Advancing Accuracy, Scalability, and Multimodal Integration,” Journal of Visualized Experiments (JoVE), no. 222, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Pegah Mansourian et al., “Deep Learning-based Anomaly Detection for Connected Autonomous Vehicles using Spatiotemporal Information,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 12, pp. 16006-16017, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Drissi Maroua, “A State-of-the-Art on Federated Learning for Vehicular Communications,” Vehicular Communications, vol. 45, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Thiruppathy Kesavan Venkatasamy et al., “Intrusion Detection System for V2X Communication in VANET Networks using Machine Learning-based Cryptographic Protocols,” Scientific Reports, vol. 14, no. 1, pp. 1-18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Xiuzhen Chen et al., “Fast and Practical Intrusion Detection System based on Federated Learning for VANET,” Computers & Security, vol. 142, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Ahmed Dawod Mohammed Ibrahum, Manzoor Hussain, and Jang-Eui Hong, “Deep Learning Adversarial Attacks and Defenses in Autonomous Vehicles: A Systematic Literature Review from a Safety Perspective,” Artificial Intelligence Review, vol. 58, no. 1, pp. 1-53, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Sanghyun Byun et al., “Secure Aggregation for Privacy-Preserving Federated Learning in Vehicular Networks,” Journal on Autonomous Transportation Systems, vol. 1, no. 3, pp. 1-25, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Levente Alekszejenkó, and Tadeusz Dobrowiecki, “A V2X-based Privacy Preserving Federated Measuring and Learning System,” arxiv preprint, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Boyu Wang, Wan Li, and Zulqarnain H. Khattak, “Anomaly Detection in Connected and Autonomous Vehicle Trajectories using LSTM Autoencoder and Gaussian Mixture Model,” Electronics, vol. 13, no. 7, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Cynthia Anthony, Walid Elgenaidi, and Muzaffar Rao, “Intrusion Detection System for Autonomous Vehicles using Non-Tree based Machine Learning Algorithms,” Electronics, vol. 13, no. 5, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Maroua Ghamri et al., “Federated Learning for Secure In-Vehicle Communication,” Telecom, vol. 6, no. 3, pp. 1-27, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Muzun Althunayyan, Amir Javed, and Omer Rana, “A Robust Multi-Stage Intrusion Detection System for In-Vehicle Network Security using Hierarchical Federated Learning,” Vehicular Communications, vol. 49, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Fatimah Aloraini, Amir Javed, and Omer Rana, “Adversarial Attacks on Intrusion Detection Systems in In-Vehicle Networks of Connected and Autonomous Vehicles,” Sensors, vol. 24, no. 12, pp. 1-29, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Hongwei Yang, and Mehdi Effatparvar, “A Deep Learning based Intrusion Detection System for CAN Vehicle based on Combination of Triple Attention Mechanism and GGO Algorithm,” Scientific Reports, vol. 15, no. 1, pp. 1-21, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Qingxin Liu et al., “Intrusion Detection System for Autonomous Vehicles using Sensor Spatio-Temporal Information,” Computers & Security, vol. 156, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Yago Romano Martinez et al., “Mitigation of Camouflaged Adversarial Attacks in Autonomous Vehicles-A Case Study using CARLA Simulator,” 2025 IEEE International Symposium on Circuits and Systems (ISCAS), London, United Kingdom, pp. 1-5, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Junjun Li et al., “A Lightweight Intrusion Detection System with Dynamic Feature Fusion Federated Learning for Vehicular Network Security,” Sensors, vol. 25, no. 15, pp. 1-22, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Tan Chen et al., “Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networks,” IEEE Transactions on Vehicular Technology, vol. 74, no. 1, pp. 1657-1673, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[24] M. Saeid HaghighiFard, and Sinem Coleri, “Secure Hierarchical Federated Learning in Vehicular Networks using Dynamic Client Selection and Anomaly Detection,” 2024 IEEE Vehicular Networking Conference (VNC), Kobe, Japan, pp. 41-48, 2024.
[CrossRef] [Google Scholar] [Publisher Link]