Transformer-based binary classification model for time series using inertial sensor data for spoofing attack detection in UAVs

V. I. Petrenko, M. Kh. Nadzhadzhra, F. B. Tebueva, D. G. Voloshin, N. Dibrov

Abstract


This paper proposes a novel binary time-series classification model, BTSC-ISD-Transformer (Binary Time-Series Classification with Inertial Sensor Data Transformer), designed for spoofing attack detection based on inertial sensor data (accelerometer and gyroscope). The model adapts the transformer architecture for time-series analysis, leveraging the self-attention mechanism to enable parallel detection of complex and long-term anomalies, in contrast to the sequential processing employed by traditional recurrent neural networks. Experimental results demonstrate the superiority of the proposed approach compared to an LSTM-RNN-based baseline model. The classification accuracy reached 97.45%, which is 12% higher than that of the LSTM-RNN model. The F1-score, Precision, and Recall achieved 96.41%, 97.03%, and 95.79%, respectively, indicating a high level of model balance and its ability to minimize both false positives and missed attacks. The results confirm the strong potential of transformer-based models for real-time cybersecurity systems in UAV applications.

Full Text:

PDF (Russian)

References


Nеровный V. V., Korataev P. D., Oblov P. S., Tolstykh M. Yu. Vulnerability characteristics of global navigation satellite system consumer equipment to spoofing attacks. Proceedings of Educational Institutions of Communications, 2023, vol. 9, no. 6, pp. 95–100. DOI: 10.31854/1813-324X-2023-9-6-95-100.

Volovik E. V. Types of spoofing (imitation interference). Proceedings of GosNIIAS. Aviation Systems Series, 2024, no. 3 (66), pp. 19–31.

Wang J., Nie L., Gu Z., Wang J., Tan R., Kumari S. Real-time GPS spoofing detection in consumer drones through multi-sensor data fusion and TimesNet. IEEE Transactions on Consumer Electronics, 2025, vol. 71, no. 2, pp. 5569–5583. DOI: 10.1109/TCE.2025.3560264.

Huang T., Wu H., Tao X., Wei Z. Prediction-based trajectory anomaly detection in UAV systems under GPS spoofing attacks. Chinese Journal of Aeronautics, 2025, vol. 38, issue 10, article no. 103478. https://doi.org/10.1016/j.cja.2025.103478.

Yang Z., Zhang Y., Zeng J., Yang Y., Jia Y., Song H., Lv T., Sun Q., An J. AI-driven safety and security for UAVs: from machine learning to large language models. Drones, 2025, vol. 9, no. 6, article no. 392. https://doi.org/10.3390/drones9060392.

Li Z., Kamarudin N. H., Kok V. J., Qamar F. Anomaly detection models in network security situational awareness based on machine learning: limitations, techniques, and future trends. IEEE Access, 2025, vol. 13, pp. 126084–126129. DOI: 10.1109/ACCESS.2025.3589620.

Averina M. D., Levanova O. A., Grushevskaya D. V., Kukharev K. A., Murin D. M., Kalinin M. A. UAV detection using neural networks. Modeling and Analysis of Information Systems, 2024, vol. 31, no. 2, pp. 182–193. DOI: 10.18255/1818-1015-2024-2-182-193.

Balyberdin A. V. Multimodal feature extraction method for network attack classification. Proceedings of Southern Federal University. Engineering Sciences, 2025, no. 3 (245), pp. 6–16. https://doi.org/10.18522/2311-3103-2025-3-6-16.

Feng C., Fan J., Liu Z., Jin G., Chen S. Unmanned aerial vehicle anomaly detection based on causality-enhanced graph neural networks. Drones, 2025, vol. 9, no. 6, article no. 408. https://doi.org/10.3390/drones9060408.

Semenyuk V., Kurmashev I., Lupidi A., Alyoshin D., Kurmasheva L., Cantelli-Forti A. Advances in UAV detection: integrating multi-sensor systems and AI for enhanced accuracy and efficiency. International Journal of Critical Infrastructure Protection, 2025, vol. 49, article no. 100744. https://doi.org/10.1016/j.ijcip.2025.100744.

Petrenko V. I., Tebueva F. B., Voloshin D. G. A method for UAV flight trajectory generation under GPS/GLONASS spoofing cyberattacks. Caspian Journal: Management and High Technologies, 2024, no. 2 (66), pp. 71–80.

Korchagin V. D. Analysis of modern state-of-the-art neural network architectures for image classification and object detection. Software Systems and Computational Methods, 2023, no. 4, pp. 73–87. DOI: 10.7256/2454-0714.2023.4.69306.

Kotenko I. V., Saenko I. B., Lauta O. S., Vasiliev N. A., Sadovnikov V. E. A method for counteracting adversarial attacks on image classification systems. Cybersecurity Issues, 2025, no. 2 (66), pp. 114–123. DOI: 10.21681/2311-3456-2025-2-114-123.

Dilek E., Dener M. An overview of transformers for video anomaly detection. Neural Computing and Applications, 2025, vol. 37, pp. 17825–17857. https://doi.org/10.1007/s00521-025-11218-1.

Jarraya I., Al-Batati A., Kadri M. B., Abdelkader M., Ammar A., Boulila W., Koubaa A. GNSS-denied unmanned aerial vehicle navigation: analysis of computational complexity, sensor fusion, and localization methodologies. Satellite Navigation, 2025, vol. 6, no. 9. https://doi.org/10.1186/s43020-025-00162-z.

Devkota B. P., Kandel L. N. Applying deep learning approaches for GPS spoofing detection in UAVs with explainable AI. In Proceedings of the 44th Digital Avionics Systems Conference (DASC), Montreal, Canada, Sept. 14–18, 2025. Available: ResearchGate.

Korium M. S., Saber M., Ahmed A. M., Narayanan A., Nardelli P. H. J. Image-based intrusion detection system for GPS spoofing cyberattacks in unmanned aerial vehicles. Ad Hoc Networks, 2024, vol. 163, article no. 103597. https://doi.org/10.1016/j.adhoc.2024.103597.

Han Y., Jia Z., He S., Zhang Y., Wu Q. CNN + transformer-based anomaly traffic detection in UAV networks for emergency rescue. arXiv preprint, 2025. https://arxiv.org/abs/2503.20355.

Ahmad M. W., Akram M. U., Mohsan M. M., Saghar K., Ahmad R., Butt W. H. Transformer-based sensor failure prediction and classification framework for UAVs. Expert Systems with Applications, 2024, vol. 248, article no. 123415. https://doi.org/10.1016/j.eswa.2024.123415.

Gamal M., Elhamahmy M., Taha S., Elmahdy H. Improving intrusion detection using LSTM-RNN to protect drone networks. Egyptian Informatics Journal, 2024, vol. 27, article no. 100501. https://doi.org/10.1016/j.eij.2024.100501.

University of New Brunswick. CIC IoT Dataset 2023 [Online]. Available: https://www.unb.ca/cic/datasets/iotdataset-2023.html (accessed: Oct. 8, 2025).

Voloshin D. G., Dibrov N. Source code repository for LSTM and transformer models: lstm-transformer-compare [Online]. Available: https://github.com/dibrovnik/lstm-transformer-compare (accessed: Oct. 8, 2025).

Kingma D. P., Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980v9, 2015. https://doi.org/10.48550/arXiv.1412.6980.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность ИТ конгресс СНЭ

ISSN: 2307-8162