Enhancing Beamforming Security in 6G Networks: LLM-Based Defense Against Adversarial Attacks
Abasi, Ammar Kamal Aloqaily, Moayad Guizani, Mohsen
Abasi, Ammar Kamal
Aloqaily, Moayad
Guizani, Mohsen
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
License
Language
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Beamforming is a critical enabler of high-capacity, low-latency communication in 6G networks, leveraging massive Multiple-Input Multiple-Output (MIMO) technology to direct signals toward intended users while minimizing interference. Recent Deep Learning (DL) advancements have enhanced beamforming efficiency by enabling data-driven beam selection. However, adopting AI-based beamforming introduces security vulnerabilities, particularly against adversarial attacks that manipulate Channel State Information (CSI) to degrade communication performance. This study proposes a Large Language Model (LLM)-enhanced defense mechanism that detects and mitigates adversarial perturbations in CSI before the beamforming model processes them. The LLM functions as an intelligent anomaly detector, distinguishing between adversarially manipulated and legitimate inputs and refining CSI features to restore accurate beamforming decisions. Unlike adversarial training, this approach does not require retraining the beamforming model, offering a lightweight and scalable solution. Experimental results demonstrate that the LLM-based defense significantly reduces the impact of adversarial attacks, improving Mean Squared Error (MSE) and Achievable Rate metrics while maintaining a robustness ratio of 0.94. The proposed method enhances the security and reliability of AI-driven beamforming without modifying the underlying neural network, making it a practical and efficient defense for 6G communication systems.
Citation
A.K. Abasi, M. Aloqaily, M. Guizani, "Enhancing Beamforming Security in 6G Networks: LLM-Based Defense Against Adversarial Attacks," 2026, pp. 3182-3187.
Source
GLOBECOM 2025 - 2025 IEEE Global Communications Conference
Conference
GLOBECOM 2025 - 2025 IEEE Global Communications Conference
Keywords
40 Engineering, 4006 Communications Engineering, 46 Information and Computing Sciences, 4613 Theory Of Computation, 7 Affordable and Clean Energy
Subjects
Source
GLOBECOM 2025 - 2025 IEEE Global Communications Conference
Publisher
IEEE