Authors : Lakshin Pathak; Mahek Shah; Shivanshi Bhatt

Volume/Issue : Volume 9 - 2024, Issue 9 - September

Google Scholar : https://tinyurl.com/bd3d7ume

Scribd : https://tinyurl.com/bddmpnch

DOI : https://doi.org/10.38124/ijisrt/IJISRT24SEP791

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : This paper presents an innovative approach for at- tack classification on Unmanned Aerial Vehicles (UAVs) using the ALBERT (A Lite BERT) transformer model. As UAVs become in- tegral to various applications, their vulnerability to cyberattacks poses significant security challenges. Traditional methods often struggle with detecting sophisticated and evolving threats. By leveraging ALBERT’s efficiency in handling large-scale data, this study enhances the detection and classification of various UAV attack types. We describe the system model, problem formulation, and the proposed ALBERT- based classification framework. The model’s performance is evaluated through experimental results, demonstrating improvements in accuracy, precision, and recall compared to existing methods. The findings underscore the po- tential of transformer-based models in cybersecurity, specifically in safeguarding UAV systems. This work also opens avenues for future research into broader applications of ALBERT in other cybersecurity domains. The proposed framework offers a practical solution for enhancing UAV security in real-world scenarios.

Keywords : UAV, Attack Classification, ALBERT Transformer, Deep Learning, Cybersecurity.

References :

1. T. M. Hoang, N. M. Nguyen, and T. Q. Duong, “Detection of eavesdrop- ping attack in uav-aided wireless systems: Unsupervised learning with one-class svm and k-means clustering,” IEEE Wireless Communications Letters, vol. 9, no. 2, pp. 139–142, 2019.
2. P.-Y. Kong, “A survey of cyberattack countermeasures for unmanned aerial vehicles,” IEEE Access, vol. 9, pp. 148244–148263, 2021.
3. Z. Lan, “Albert: A lite bert for self-supervised learning of language representations,” arXiv preprint arXiv:1909.11942, 2019.
4. R. Shrestha, A. Omidkar, S. A. Roudi, R. Abbas, and S. Kim, “Machine- learning-enabled intrusion detection system for cellular connected uav networks,” Electronics, vol. 10, no. 13, p. 1549, 2021.
5. T. Lagkas, V. Argyriou, S. Bibi, and P. Sarigiannidis, “Uav iot framework views and challenges: Towards protecting drones as “things”,” Sensors, vol. 18, no. 11, p. 4015, 2018.