Detection of GPS Attacks on Unmanned Aerial Vehicles with Multiclass Classification

• Gustavo Gualberto Rocha de Lemos UFABC
• Rodrigo Augusto Cardoso da Silva UFABC

DOI: https://doi.org/10.5753/sbseg.2024.241445

Abstract

Unmanned aerial vehicles (UAVs) are increasingly being employed across various domains. These vehicles usually rely on the Global Positioning System (GPS), which makes them vulnerable to attacks based on fake GPS signals. Hence, this paper proposes an Intrusion Detection System (IDS) that utilizes machine learning techniques to detect and identify GPS Jamming and three types of GPS Spoofing attacks. The proposed multiclass classifier enables the identification of the attack type – an essential factor in determining the most effective protective measures. The achieved accuracy rate was 98.08%, with 2.6% false negatives, lowering the likelihood of overlooking attacks, which is crucial in real UAV deployments.

References

Aissou, G., Benouadah, S., El Alami, H., and Kaabouch, N. (2022). Instance-based supervised machine learning models for detecting GPS spoofing attacks on UAS. In 2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC), pages 0208–0214.

Aissou, G., Slimane, H. O., Benouadah, S., and Kaabouch, N. (2021). Tree-based supervised machine learning models for detecting GPS spoofing attacks on UAS. In 2021 IEEE 12th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pages 0649–0653.

Bauernfeind, R., Kraus, T., Dötterböck, D., Eissfeller, B., Loehnert, E., and Wittmann, E. (2011). Car jammers: Interference analysis. GPS World, 22:28–35.

Burkov, A. (2019). The Hundred-Page Machine Learning Book. Andriy Burkov, Quebec.

da Silva, D. A. M. (2017). Gps jamming and spoofing using software defined radio. Master’s thesis, University Institute of Lisbon.

da Silva, R. A. C., da Fonseca, N. L. S., and Boutaba, R. (2021). Evaluation of the employment of UAVs as fog nodes. IEEE Wireless Communications, 28(5):20–27.

Davidovich, B., Nassi, B., and Elovici, Y. (2022). Towards the detection of GPS spoofing attacks against drones by analyzing camera’s video stream. Sensors, 22(7).

Derhab, A., Cheikhrouhou, O., Allouch, A., Koubaa, A., Qureshi, B., Ferrag, M. A., Maglaras, L., and Khan, F. A. (2023). Internet of drones security: Taxonomies, open issues, and future directions. Vehicular Communications, 39:100552.

Gasimova, A., Khoei, T. T., and Kaabouch, N. (2022). A comparative analysis of the ensemble models for detecting GPS spoofing attacks on UAVs. In 2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC), pages 0310–0315.

Géron, A. (2023). Hands-On Machine Learning with ScikitLearn, Keras, and Tensor-Flow. O’Reilly Media, Sebastopol.

Haider, Z. and Khalid, S. (2016). Survey on effective GPS spoofing countermeasures. In 2016 Sixth International Conference on Innovative Computing Technology (INTECH), pages 573–577.

Khan, A., Gupta, S., and Gupta, S. K. (2022). Emerging UAV technology for disaster detection, mitigation, response, and preparedness. Journal of Field Robotics, 39(6):905–955.

Khoei, T. T., Aissou, G., Al Shamaileh, K., Devabhaktuni, V. K., and Kaabouch, N. (2023). Supervised deep learning models for detecting GPS spoofing attacks on unmanned aerial vehicles. In 2023 IEEE International Conference on Electro Information Technology (eIT), pages 340–346.

Khoei, T. T., Gasimova, A., Ahajjam, M. A., Shamaileh, K. A., Devabhaktuni, V., and Kaabouch, N. (2022). A comparative analysis of supervised and unsupervised models for detecting GPS spoofing attack on UAVs. In 2022 IEEE International Conference on Electro Information Technology (eIT), pages 279–284.

Lemos, G. (2023). Original dataset. [link].

Misra, P. and Enge, P. (2006). Global Position System Signals, Measurement and Performance. Ganga Jamuna Press, Lincoln.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.

Ranyal, E. and Jain, K. (2021). Unmanned aerial vehicle’s vulnerability to GPS spoofing a review. Indian Society of Remote Sensing, 49:585–591.

Talaei Khoei, T., Ismail, S., and Kaabouch, N. (2022). Dynamic selection techniques for detecting GPS spoofing attacks on UAVs. Sensors, 22(2).

Talaei Khoei, T., Ismail, S., Shamaileh, K. A., Devabhaktuni, V. K., and Kaabouch, N. (2023). Impact of dataset and model parameters on machine learning performance for the detection of GPS spoofing attacks on unmanned aerial vehicles. Applied Sciences, 13(1).

Wei, X., Wang, Y., and Sun, C. (2022). Perdet: Machine-learning-based UAV GPS spoofing detection using perception data. Remote Sensing, 14(19).

Whelan, J., Almehmadi, A., and El-Khatib, K. (2022). Artificial intelligence for intrusion detection systems in unmanned aerial vehicles. Computers and Electrical Engineering, 99:107784.

Wolpert, D. H. (1996). The Lack of A Priori Distinctions Between Learning Algorithms. Neural Computation, 8(7):1341–1390.