E-ISSN 2705-3954 | ISSN 0794-4756
 
2026, Vol: 33, Issue: 2
33 / 2Current Issue Online FirstArchiveAims and ScopeAbstracting & IndexingMost Accessed ArticlesMost Downloaded ArticlesMost Cited Articles

Original Research 


Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks

Mustapha Lawan, Ashraf Adam Ahmad, Isah Musa Danjuma, Fatai Olatunde Adunola, Abdullahi Ahamad Shehu.


Abstract
ABSTRACT
Primary User Emulation Attacks (PUEAs) are attacks that cause a serious threat to Cognitive Radio Networks (CRNs). In this type of attack, malicious users mimic a legitimate primary signal that led to a severe degradation of spectrum utilization. Most of the PUEA detection techniques often rely on prior knowledge of attack characteristics, which exhibit poor performance at low signal to noise ratios (SNR) and fail to identify previously unseen attack modulations. To mitigate these challenges, this paper has proposed a hybrid deep learning framework that combines the Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Extreme Value Theory (EVT)-based OpenMax for open-set PUEA detection under Rayleigh fading conditions. Multi-domain signal features were extracted that enable reliable identification of known and unknown attackers, which is proposed in this method. This approach does not require prior knowledge of the attack. The dataset used for the evaluation of the model is simulated data that contain 20,000 signal realizations with four classes generated over an SNR that ranges from −10 to +10 dB under Rayleigh fading with additive white Gaussian noise. The results show that the proposed approach outperforms the conventional energy detection and cyclostationary methods by achieving an accuracy of 99.96% and 92.40% for both the closed and open sets, respectively, with an AUROC of 0.9803.

Key words: Cognitive Radio Networks; CNN-GRU; Primary User Emulation Attack; Open-Set Detection; Extreme Value Theory; Rayleigh Fading; Multi-Domain Feature Extraction.


 
ARTICLE TOOLS
Abstract
PDF Fulltext
How to cite this articleHow to cite this article
Citation Tools
Related Records
 Articles by Mustapha Lawan
Articles by Ashraf Adam Ahmad
Articles by Isah Musa Danjuma
Articles by Fatai Olatunde Adunola
Articles by Abdullahi Ahamad Shehu
on Google
on Google Scholar


How to Cite this Article
Pubmed Style

Lawan M, Ahmad AA, Danjuma IM, Adunola FO, Shehu AA. Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks. NJE. 2026; 33(2): 37-46. doi:10.5455/nje.2026.33.02.05

Web Style

Lawan M, Ahmad AA, Danjuma IM, Adunola FO, Shehu AA. Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks. https://www.njeabu.com.ng/?mno=318213 [Access: September 28, 2026]. doi:10.5455/nje.2026.33.02.05

AMA (American Medical Association) Style

Lawan M, Ahmad AA, Danjuma IM, Adunola FO, Shehu AA. Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks. NJE. 2026; 33(2): 37-46. doi:10.5455/nje.2026.33.02.05


Vancouver/ICMJE Style

Lawan M, Ahmad AA, Danjuma IM, Adunola FO, Shehu AA. Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks. NJE. (2026), [cited September 28, 2026]; 33(2): 37-46. doi:10.5455/nje.2026.33.02.05


Harvard Style

Lawan, M., Ahmad, . A. A., Danjuma, . I. M., Adunola, . F. O. & Shehu, . A. A. (2026) Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks. NJE, 33 (2), 37-46. doi:10.5455/nje.2026.33.02.05


Turabian Style

Lawan, Mustapha, Ashraf Adam Ahmad, Isah Musa Danjuma, Fatai Olatunde Adunola, and Abdullahi Ahamad Shehu. 2026. Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks. Nigerian Journal of Engineering, 33 (2), 37-46. doi:10.5455/nje.2026.33.02.05


Chicago Style

Lawan, Mustapha, Ashraf Adam Ahmad, Isah Musa Danjuma, Fatai Olatunde Adunola, and Abdullahi Ahamad Shehu. "Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks." Nigerian Journal of Engineering 33 (2026), 37-46. doi:10.5455/nje.2026.33.02.05


MLA (The Modern Language Association) Style

Lawan, Mustapha, Ashraf Adam Ahmad, Isah Musa Danjuma, Fatai Olatunde Adunola, and Abdullahi Ahamad Shehu. "Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks." Nigerian Journal of Engineering 33.2 (2026), 37-46. Print. doi:10.5455/nje.2026.33.02.05


APA (American Psychological Association) Style

Lawan, M., Ahmad, . A. A., Danjuma, . I. M., Adunola, . F. O. & Shehu, . A. A. (2026) Hybrid Deep Learning and Multi-domain Feature Extraction for Detecting Primary User Emulation Attacks In Cognitive Radio Networks. Nigerian Journal of Engineering, 33 (2), 37-46. doi:10.5455/nje.2026.33.02.05


Author LoginReviewer LoginAbout PublisherOpen Access PolicyEditorial Review PolicyPeer Review PolicyEditorial & Peer Review ProcessPublication Ethics and Publication Malpractice StatementPlagiarism PolicyPolicy on the Use of Generative Artificial Intelligence (GenAI)

About Nigerian Journal of Engineering

Nigerian Journal of Engineering is an open-access, peer-reviewed scholarly journal published by the Faculty of Engineering, Ahmadu Bello University, Zaria ... Read more.



For best results, please use Internet Explorer or Google Chrome.

Contact Information

The Editor–in–Chief

Nigerian Journal of Engineering

Faculty of Engineering

Ahmadu Bello University

Samaru - Zaria Nigeria

E-mails:

njeabu@yahoo.com; abkunya@abu.edu.ng