Gaussian Mixture Model-Based Anomaly Detection for Defense Against Byzantine Attack in Cooperative Spectrum Sensing

Parmar, Ashok ORCID: 0000-0003-1137-043X, Shah, Karan ORCID: 0000-0003-3588-2974, Captain, Kamal M ORCID: 0000-0003-0865-137X, López-Benítez, Miguel ORCID: 0000-0003-0526-6687 and Patel, Jignesh R ORCID: 0000-0003-4002-4237 (2024) Gaussian Mixture Model-Based Anomaly Detection for Defense Against Byzantine Attack in Cooperative Spectrum Sensing. IEEE Transactions on Cognitive Communications and Networking, 10 (2). pp. 499-509.

Text
IEEE_TCCN_2024.pdf - Author Accepted Manuscript
Available under License Creative Commons Attribution.
Download (8MB) | Preview

Official URL: http://dx.doi.org/10.1109/tccn.2023.3342409

Abstract

Cognitive radio (CR) serves as an effective solution to the spectrum scarcity issue in current wireless communication. Spectrum sensing is one of the key enabling technologies for CR. Spectrum sensing based on single user detection often suffers from wireless channel ailments such as path loss, fading, and shadowing. Cooperative spectrum sensing (CSS) is proposed to overcome these adverse channel effects. However, CSS is often an easy target for malicious users (MUs). The Byzantine attack is a major hurdle in the success of the CR. Hence, the identification of MUs in the CR network is essential to improve the detection performance of CSS. In this work, we propose a Gaussian mixture model based anomaly detection algorithm for the identification of MUs. We first show that the presence of MUs degrades the CSS performance. Theoretical analysis is carried out to understand the intuition behind the proposed algorithm. The effectiveness of the proposed algorithm in detecting attackers is demonstrated for different attack scenarios. The performance of the proposed algorithm in detecting MUs is compared with existing algorithms. Based on the MU detection algorithm, a weighted sum based CSS algorithm is proposed that can eliminate the effects of attackers on the CSS performance.

Item Type:	Article
Divisions:	Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	04 Dec 2023 11:45
Last Modified:	01 May 2024 21:36
DOI:	10.1109/tccn.2023.3342409
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3177154