Intelligent Detection of Spoofing Attack in Single-Frequency GNSS Receivers Using Density-Based Automatic Spatial Clustering Algorithm in Noisy Environment

Delnavaz, Amin Mahdi; Shamsi, Alireza; Shafiee, Ebrahim

doi:10.22034/jsst.2025.1558

Intelligent Detection of Spoofing Attack in Single-Frequency GNSS Receivers Using Density-Based Automatic Spatial Clustering Algorithm in Noisy Environment

Document Type : Original Research Paper

Authors

Amin Mahdi Delnavaz

Alireza Shamsi

Ebrahim Shafiee

Department of Telecommunications, Faculty of Electrical Engineering, Shahid Sattari University of Aeronautical Sciences and Technology, Tehran, Iran

10.22034/jsst.2025.1558

Abstract

With the growing application of Global Navigation Satellite Systems (GNSS), ensuring the security of these systems has become a critical priority. Among the various threats targeting GNSS, spoofing attacks pose the greatest danger, as they exploit the inability of GPS receivers to distinguish between authentic and spoofed signals. This vulnerability can lead to incorrect navigation equation solutions, ultimately resulting in erroneous position estimations. Due to the lack of a universal method for detecting spoofing attacks, various approaches have been proposed, tailored to specific requirements. One prominent category involves the use of unsupervised machine learning clustering algorithms. While density-based clustering algorithms have demonstrated promising performance, their effectiveness is often limited by a strong dependence on input parameters. In this study, spoofing signals are detected using the HDBSCAN algorithm, a hierarchical density-based clustering approach. The algorithm distinguishes spoofing signals by analyzing signal phase, cross-correlation norm, and the power differential between spoofed and genuine signals. The algorithm's performance is assessed using the Silhouette index, Dunn index, and Confusion Matrix metrics. Field tests validated the proposed algorithm, which was implemented on a software-defined receiver. The results demonstrated a spoofing signal detection accuracy of 98.43%.

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Keywords

Machine Learning

Positioning

HDBSCAN clustering

Spoofing attack

GPS Software Receiver

Subjects

GPS and navigation GPS)، GLONASS، GALILEO

Article Title Persian

شناسایی هوشمند حمله فریب در گیرنده‌های تک فرکانسه GNSS با استفاده از الگوریتم خوشه‌بندی خودکار فضایی مبتنی بر چگالی در محیط نویزی

Authors Persian

امین مهدی دلنواز

علیرضا شمسی

ابراهیم شفیعی

گروه مخابرات دانشکده برق علوم و فنون هوایی شهید ستاری

Abstract Persian

باتوجه‌به گسترش کاربرد سامانه‌های موقعیت‌یاب جهانی GNSS، حفاظت از این سامانه به یکی از مهم‌ترین اقدامات بدل شده است. از میان حملات به این سامانه‌ها خطرناک‌ترین حملات مربوط به حمله فریب است؛ زیرا که در این حمله گیرنده سیگنال GPS نمی‌تواند بین سیگنال اصلی و سیگنال فریب تمایز قائل شود. این امر موجب حل اشتباه معادلات ناوبری و در نهایت تشخیص موقعیت اشتباه می‌شود. به علت عدم وجود یک روش یکتا برای شناسایی حمله فریب؛ روش‌های گوناگونی وجود دارند که باتوجه‌به نیاز مورداستفاده قرار می‌گیرند. یک دسته از روش‌ها استفاده از الگوریتم‌های خوشه‌بندی یادگیری ماشین بدون ناظر است. الگوریتم‌های خوشه‌بندی مبتنی بر چگالی هر چند که رویکرد خوبی از خود نشان می‌دهند بااین‌وجود به علت وابستگی شدید به پارامترهای ورودی آن چنان کارآمد نخواهند بود. در این مقاله با الگوریتم HDBSCAN که الگوریتمی سلسله‌مراتبی مبتنی بر چگالی است؛ سیگنال فریب آشکارسازی می‌گردد. این الگوریتم با تحلیل فاز، نرم هم‌بسته گیری و توان سیگنال فریب نسبت به سیگنال اصلی، جعلی بودن آن را تشخیص می‌‌دهد. برای بررسی عملکرد این الگوریتم از شاخص‌های Silhouette، Dunn و Confusion Matrix استفاده می‌شود. در آزمون‌های میدانی، الگوریتم پیشنهادی بر روی گیرنده نرم‌افزاری پیاده‌سازی و بادقت 98/43 درصد سیگنال فریب را به‌درستی تشخیص می‌دهد.

Keywords Persian

یادگیری ماشین

موقعیت‌یابی

خوشه‌بندی HDBSCAN

حمله فریب

گیرنده نرم‌افزاری GPS

[1] T. R. Das, S. Hasan, S. Sarwar, J. K. Das, and M. A. Rahman, "Facial spoof detection using support vector machine," in Proceedings of International Conference on Trends in Computational and Cognitive Engineering: Proceedings of TCCE 2020, 2021: Springer, pp. 615-625, https://doi.org/10.1007/978-981-33-4673-4_50.

[2] R. A. Sowah, K. B. Ofori-Amanfo, G. A. Mills, and K. M. Koumadi, "Detection and prevention of man-in-the-middle spoofing attacks in MANETs using predictive techniques in Artificial Neural Networks (ANN)," Journal of Computer Networks and Communications, vol. 2019, 2019, Art. no. 4683982, https://doi.org/10.1155/2019/4683982.

[3] E. Shafiee, M. R. Mosavi, and M. Moazedi, "Detection of spoofing attack using machine learning based on multi-layer neural network in single-frequency GPS receivers," The Journal of Navigation, vol. 71, no. 1, pp. 169-188, 2018, https://doi.org/10.1017/S0373463317000558.

[4] K. Radoš, M. Brkić, and D. Begušić, "Recent advances on jamming and spoofing detection in GNSS," Sensors, vol. 24, no. 13, 2024, Art. no. 4210, https://doi.org/10.3390/s24134210.

[5] Z. Sarpanah, M. R. Mosavi, and E. Shafiee, "GPS receivers spoofing detection based on subtractive, FCM and DBScan clustering algorithms," Journal of Circuits, Systems and Computers, vol. 32, no. 9, 2023, Art. no. 2350152, https://doi.org/10.1142/S0218126623501529.

[6] T. Talaei Khoei, S. Ismail, and N. Kaabouch, "Dynamic selection techniques for detecting GPS spoofing attacks on UAVs," Sensors, vol. 22, no. 2, 2022, Art. no. 662, https://doi.org/10.3390/s22020662.

[7] L. Wang, P. Chen, L. Chen, and J. Mou, "Ship AIS trajectory clustering: An HDBSCAN-based approach," Journal of Marine Science and Engineering, vol. 9, no. 6, 2021, Art. no. 566, https://doi.org/10.3390/jmse9060566.

[8] M. de Berg, A. Gunawan, and M. Roeloffzen, "Faster DB-scan and HDB-scan in low-dimensional Euclidean spaces," arXiv preprint arXiv:1702.08607, 2017, https://doi.org/10.48550/arXiv.1702.08607.

[9] E. Schubert, J. Sander, M. Ester, H. P. Kriegel, and X. Xu, "DBSCAN revisited, revisited: why and how you should (still) use DBSCAN," ACM Transactions on Database Systems (TODS), vol. 42, no. 3, pp. 1-21, 2017, v Art. no.19, https://doi.org/10.1145/3068335.

[10] T. V. Sai Krishna, A. Yesu Babu, and R. Kiran Kumar, "Determination of optimal clusters for a Non-hierarchical clustering paradigm K-Means algorithm," in Proceedings of International Conference on Computational Intelligence and Data Engineering, Singapore: Springer, 2018, pp. 301-316, https://doi.org/10.1007/978-981-10-6319-0_26.

[11] J. C. Dunn, "A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters," Journal of Cybernetics, vol. 3, no. 3, pp. 32-57, 1973, https://doi.org/10.1080/01969727308546046.

[12] Z. Huang, "Extensions to the k-means algorithm for clustering large data sets with categorical values," Data Mining and Knowledge Discovery, vol. 2, no. 3, pp. 283-304, 1998, https://doi.org/10.1023/A:1009769707641.

[13] H. Qiu, Y. Liu, N. A. Subrahmanya, and W. Li, "Granger causality for time-series anomaly detection," in 2012 IEEE 12th International Conference on Data Mining, 2012: IEEE, pp. 1074-1079, https://doi.org/10.1109/ICDM.2012.73.

[14] M. Ankerst, M. M. Breunig, H.-P. Kriegel, and J. Sander, "OPTICS: Ordering points to identify the clustering structure," ACM Sigmod Record, vol. 28, no. 2, pp. 49-60, 1999, https://doi.org/10.1145/304181.304187.

[15] M. R. Mosavi, M. J. Rezaei, N. Hosseinzadeh, R. A. Kiaamiri, “Two New Intelligent Methods for Detecting and Cancelling Spoofing Effects on GPS Receivers”, Journal of Electronic & Cyber Defence, vol. 2, no. 1, pp.71-81, 2014, (In Persian).

[16] J. C. Bezdek, R. Ehrlich, and W. Full, "FCM: The fuzzy c-means clustering algorithm," Computers & Geosciences, vol. 10, no. 2-3, pp. 191-203, 1984, https://doi.org/10.1016/0098-3004(84)90020-7.

[17] G. Stewart and M. Al-Khassaweneh, "An implementation of the HDBSCAN* clustering algorithm," Applied Sciences, vol. 12, no. 5, 2022, Art. no. 2405, https://doi.org/10.3390/app12052405.

[18] K. Khan, S. U. Rehman, K. Aziz, S. Fong, and S. Sarasvady, "DBSCAN: Past, present and future," in The fifth international conference on the applications of digital information and web technologies (ICADIWT 2014), 2014: IEEE, pp. 232-238, https://doi.org/10.1109/ICADIWT.2014.6814687.

[19] N. Dhanachandra, K. Manglem, and Y. J. Chanu, "Image segmentation using K-means clustering algorithm and subtractive clustering algorithm," Procedia Computer Science, vol. 54, pp. 764-771, 2015, https://doi.org/10.1016/j.procs.2015.06.090.

[20] E. Shafiee, S. M. R. Mosavi, and M. Moazedi, "Detection of Spoofing Attack Based on Multi-Layer Neural Network in Single-Frequency GPS Receivers," Journal of Electronic and Cyber Defence, vol. 3, no. 1, pp. 69-80, 2015.

[21] E. Shafiee, M. R. Mosavi, and M. Moazedi, "A modified imperialist competitive algorithm for spoofing attack detection in single-frequency GPS receivers." Wireless Personal Communications, vol. 119, pp. 919-940, 2021, https://doi.org/10.1007/s11277-021-08244-2.