IoT-Enabled Network Architecture and Security Framework for Autonomous Flying Car Systems

Abstract

The emergence of autonomous flying cars presents a revolutionary approach to urban mobility, requiring a robust, low-latency, and secure communication network. This paper proposes an IoT-enabled network architecture tailored for flying car systems, integrating real-time telemetry, navigation data, and vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communications. The framework emphasizes security and anomaly detection to safeguard against cyber-attacks, unauthorized access, and communication failures. Simulation results demonstrate that the proposed IoT-based architecture ensures efficient data exchange, high reliability, and adaptive security, enabling safe and coordinated flight operations in dynamic urban environments. The study highlights the potential of IoT technologies to enhance the scalability, safety, and operational efficiency of autonomous aerial transport systems.

Introduction

The rise of autonomous flying cars promises faster, congestion-free urban transportation but introduces critical challenges in communication, coordination, and security. Flying cars depend on IoT-enabled networks for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, requiring low-latency, high-reliability connections. Traditional vehicular networks are inadequate for these highly dynamic aerial environments, and the open nature of IoT exposes systems to cyber threats and anomalies.

To address these challenges, the paper proposes a hybrid IoT-based network architecture with integrated security and real-time anomaly detection. The system leverages machine learning, deep learning, and edge-cloud computing to ensure safe, efficient, and scalable urban air mobility.

Literature Survey Highlights

• UAV and Flying Car Networks: Adaptive IoT frameworks ensure reliable connectivity and safe operation in dynamic airborne environments.

• Security Enhancements: Blockchain, decentralized architectures, lightweight cryptography, and anomaly detection improve data integrity and resilience against cyber threats.

• Machine Learning & AI: Hybrid ML frameworks, deep reinforcement learning, federated learning, swarm intelligence, and fuzzy clustering improve anomaly detection, latency, and network throughput.

• Predictive & Real-Time Monitoring: IoT-driven predictive maintenance, YOLO-based vehicle detection, and CNN-RN models enhance situational awareness, threat detection, and operational safety.

• Cross-Domain Insights: Studies in healthcare, virtualization, and industrial IoT demonstrate the importance of robust, adaptive anomaly detection models for high-stakes, dynamic networks.

Overall, the research trajectory moves from traditional UAV networks to IoT-enabled, AI-driven, secure, and optimized architectures suitable for urban flying car ecosystems.

Proposed Model

The hybrid anomaly detection system integrates multiple modules to monitor, detect, and respond to anomalies in real time.

1. Dataset Module

   • Collects telemetry, network traffic (V2V/V2I), environmental data (GPS, lidar/radar, weather), and security logs.

   • Preprocessing includes noise reduction, normalization, feature extraction (relative speed, obstacle proximity, signal strength).

2. Data Preprocessing Module

   • Cleans, scales, and transforms raw sensor/network data into actionable features.

   • Uses dimensionality reduction (PCA/Autoencoders) to improve computational efficiency.

3. Anomaly Detection Module

   • Supervised models (Random Forest, XGBoost) detect known anomalies (communication failures, unauthorized access, abnormal maneuvers).

   • Unsupervised models (Autoencoders, LSTM, Isolation Forest) detect novel or unexpected deviations.

   • Hybrid fusion combines model outputs via weighted voting or threshold rules to reduce false positives.

4. Edge and Cloud Computing Module

   • Edge: Real-time detection and immediate responses onboard each vehicle.

   • Cloud: Aggregates data, applies advanced deep learning, and updates edge models through federated learning for continuous improvement.

5. Security and Alert Module

   • Generates alerts and triggers automated mitigation (rerouting, communication isolation, emergency maneuvers).

   • Logs anomalies for auditing, retraining, and adaptive learning.

6. Implementation

   • Integrates IoT data, ML/DL models, and edge-cloud computing to provide scalable, adaptive, and secure flying car networks.

   • Ensures real-time monitoring, anomaly detection, and proactive response for operational safety.

Results

Anomaly Detection Performance Metrics:

Key Observations:

• The hybrid model outperforms individual approaches in accuracy, precision, recall, and F1-score.

• False positives are reduced to 4.5%, enhancing reliability for real-time deployment.

• Detection times are under 55 milliseconds, ensuring suitability for high-speed, safety-critical aerial operations.

• The system effectively detects network, operational, and environmental anomalies, maintaining high sensitivity and robustness.

Conclusion

This paper presents a comprehensive framework for an IoT-enabled flying car network with integrated anomaly detection and security mechanisms. The proposed model leverages multi-source IoT data, including telemetry, network traffic, environmental sensors, and security logs, combined with hybrid machine learning techniques to detect both known and novel anomalies in real time. By integrating edge computing for low-latency processing and cloud-based model aggregation with federated learning, the system ensures scalability, adaptability, and continuous improvement. The results demonstrate that the hybrid approach significantly outperforms standalone supervised or unsupervised models, achieving an accuracy of 95.7%, a precision of 93.6%, and an F1-score of 93.0%, while maintaining a low false-positive rate of 4.5%. Scenario-based evaluation further confirms the model’s effectiveness in detecting communication failures, unauthorized access attempts, abnormal flight patterns, and environmental disturbances within milliseconds, making it suitable for real-time deployment. Overall, the proposed framework establishes a robust, reliable, and adaptive solution for the safe operation of autonomous flying car networks, providing enhanced anomaly detection, proactive security, and operational efficiency essential for next-generation urban air mobility systems.

References

[1] M. Dai, N. Huang, Y. Wu, J. Gao, and Z. Su, “Unmanned Aerial Vehicle Assisted Wireless Networks: Advancements, Challenges, and Solutions,” IEEE Internet of Things Journal, vol. 10, no. 5, pp. 4117–4147, 2022, doi: 10.1109/JIOT.2022.3230786. [2] J. Sharma and P. S. Mehra, “Secure communication in IOT based UAV networks: A systematic survey,” Internet of Things, vol. 23, p. 100883, 2023, doi: 10.1016/j.iot.2023.100883. [3] P. Draugelyt? and I. Suzdalev, “Blockchain-based secure communication for UAV networks: A decentralized approach to GNSS spoofing detection,” Aviation, vol. 29, no. 3, pp. 191–200, 2025, doi: 10.3846/aviation.2025.24463. [4] S. Kaur, N. Arya, and S. Singh, “Optimizing UAV IoT Network Integration: A Scalable Multi Objective Communication Framework,” Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 17996–18003, 2024, doi: 10.48084/etasr.8589. [5] A. Andreou et al., “UAV-assisted IoT network framework with hybrid deep reinforcement and federated learning,” Scientific Reports, vol. 15, Art. no. 37107, 2025, doi: 10.1038/s41598-025-21014-5. [6] P. Joshi, A. Kalita, and M. Gurusamy, “Reliable and Efficient Data Collection in UAV-based IoT Networks,” arXiv, Nov. 2023. [7] A. Mallesh, “Autonomous Security Response Architecture for Flight Path Anomaly Detection in Defense Drone Systems,” Journal of Computer Science and Technology Studies, vol. 7, no. 8, pp. 652–662, 2025, doi: 10.32996/jcsts.2025.7.8.75. [8] Y. K. Gupta, S. Reddy Gaddam, H. Gupta and S. Banerjee, \"An Optimized Swarm Intelligence Approach for Fuzzy Clustering-Based Intrusive Behavior Detection in IoT and Network System,\" 2025 IEEE Madhya Pradesh Section Conference (MPCON), Jabalpur, India, 2025, pp. 864-870, doi: 10.1109/MPCON66082.2025.11256633. [9] Mr Sasidhar Reddy Gaddam and DOI: 10.48047/IJCNIS.16.1.458, “An Enhanced Hybrid Machine Learning Approach For Efficient Botnet Attack Detection In Internet Of Things Networks”, Int. j. commun. netw. inf. secur., vol. 16, no. 1, pp. 449–458, Jan. 2024. [10] Chaitanya , G. K. ., Gaddam, S. R. . ., Ahmad , K. S. F. ., Vicharapu, B. ., Soundharya, U. L. . ., & Madhuri , U. N. L. . (2025). A Multimodal Approach to Digital Security: Combining Steganography, ?Watermarking, and Image Enhancement. International Journal of Basic and Applied Sciences, 14(2), 611-619. [11] J. Manikandan, V. Vemulapalli, K. Spandana, S. Vikruthi, B. Lakshmikanth and M. Radhika, \"Studying the Linear Degree of Community Network Patterns to Eliminate Misclassification Trouble the use of Gaining Knowledge of Approaches,\" 2025 International Conference on Computing Technologies (ICOCT), Bengaluru, India, 2025, pp. 1-5, doi: 10.1109/ICOCT64433.2025.11118921. [12] Srilakshmi, U. & Manikandan, J. & Valluru, Dinesh & Panyala, Amerendra & Prasad, Baddepaka & Nagavamsi, Mireyala. (2025). An IoT-Driven Machine Learning Model for Predictive Maintenance Classification in Industrial Systems. 10.1007/978-981-96-7222-6_37. [13] Manikandan, J & Srilakshmi, U.. (2024). Deep Learning-Based Vulnerability Detection and Mitigation in Virtualization Data Center. International Journal of Maritime Engineering. 1. 647-662. 10.5750/ijme.v1i1.1393. [14] S. Badonia, M. V. Babu, N. R. Lakkimsetty, G. Kavitha and A. P. N, \"Implication and Challenges in Modernisation of Healthcare System using 5G,\" 2024 1st International Conference on Advances in Computing, Communication and Networking (ICAC2N), Greater Noida, India, 2024, pp. 834-837, doi: 10.1109/ICAC2N63387.2024.10894954. [15] R. Shaik, M. V. Babu, S. Medichelimi, C. Paritala, A. Amaranayani and I. Narasimharao, \"Physical Layer Security for WSNs: Addressing Eavesdropping and Energy Constraints,\" 2025 7th International Conference on Inventive Material Science and Applications (ICIMA), Namakkal, India, 2025, pp. 27-32, doi: 10.1109/ICIMA64861.2025.11074037. [16] K. Pande, V. Babu, V. Tripathi, P. K, N. Bhatt and Manjuvani, \"Dynamic Security and Efficiency Improvements in IoT Through Enhanced Security Bounds Framework,\" 2025 2nd International Conference On Multidisciplinary Research and Innovations in Engineering (MRIE), Gurugram, India, 2025, pp. 562-566, doi: 10.1109/MRIE66930.2025.11156654. [17] Vikruthi, S., Archana, M., & Tanguturi, R. C. (2023). A novel framework for vehicle detection and classification using enhanced YOLO-v7 and GBM to prioritize emergency vehicle. Int. J. Intell. Syst. Appl. Eng, 12(1s). [18] S. Vikruthi, T. R. Singasani, V. T. R. P. K. M, P. V. V. S. D. Nagendrudu, C. Raghavendra and R. Sahith, \"Detection of Emergency Vehicles in Traffic and Assign Traffic Free Path Using Deep Learning,\" 2025 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL), Bhimdatta, Nepal, 2025, pp. 1252-1261, doi: 10.1109/ICSADL65848.2025.10933032. [19] Yarra, Khyathisree, Prasanthi Boyapati, LV Siva Rama Krishna Boddu, and Saibaba Velidi. \"Used Car Price Forecasting: A Machine Learning-Based Approach.\" In Algorithms in Advanced Artificial Intelligence, pp. 465-470. CRC Press, 2025. [20] Krishna, Boddu & Mahalakshmi, V. & Gopala Krishna Murthy, Nookala. (2023). Modelling a stacked dense network model for outlier prediction over medical-based heart prediction data. Journal of High Speed Networks. 29. 1-16. 10.3233/JHS-222079. [21] M. V. Babu, V. Ramya, and V. S. Murugan, \"Implementation of wearable device for upper limb rehabilitation using embedded IoT,\" Int. J. Electron. Signals Syst. Manag. Sci., vol. 16, no. 1, pp. 90–95, Mar. 2024. [Online]. Available: https://doi.org/10.1504/IJESMS.2024.136972 [22] M. V. . Babu, V. . Ramya, and V. S. . Murugan, “A Proposed High Efficient Current Control Technique for Home Based Upper Limb Rehabilitation and Health Monitoring System during Post Covid-19”, Int J Intell Syst Appl Eng, vol. 12, no. 2s, pp. 600–607, Oct. 2023. [23] Mr Sasidhar Reddy Gaddam and DOI : 10.48047/IJCNIS.14.3.1283, “Java-Driven Trustworthy And Reliable Deep Learning For Cyberattack Detection In Industrial Iot”, Int. j. commun. netw. inf. secur., vol. 14, no. 3, pp. 1274–1283, Apr. 2022.

Copyright

Copyright © 2026 V T Ram Pavan Kumar, V Mohana Priya, Y Anjaneyulu, Swargam Anusha, U Lakshmi Prasanna, B R Amarendra Nath Chowdary, Tejaswi Matram, MD Taufeeq Shariff. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.