Security Concerns on Machine Learning Solutions for 6G Networks in mmWave Beam Prediction

TL;DR

This paper addresses security vulnerabilities in 6G mmWave beam prediction models by proposing an adversarial learning mitigation method to defend against attacks, ensuring model robustness and security in future wireless networks.

Contribution

It introduces a novel adversarial learning-based mitigation technique specifically designed for 6G mmWave beam prediction models to enhance security against adversarial attacks.

Findings

Defended models show mean square errors close to attack-free models under adversarial attack.

The proposed mitigation method effectively reduces the impact of fast gradient sign method attacks.

Security of 6G machine learning models can be significantly improved with adversarial training.

Abstract

6G -- sixth generation -- is the latest cellular technology currently under development for wireless communication systems. In recent years, machine learning algorithms have been applied widely in various fields, such as healthcare, transportation, energy, autonomous car, and many more. Those algorithms have been also using in communication technologies to improve the system performance in terms of frequency spectrum usage, latency, and security. With the rapid developments of machine learning techniques, especially deep learning, it is critical to take the security concern into account when applying the algorithms. While machine learning algorithms offer significant advantages for 6G networks, security concerns on Artificial Intelligent (AI) models is typically ignored by the scientific community so far. However, security is also a vital part of the AI algorithms, this is because the AI model itself can be poisoned by attackers. This paper proposes a mitigation method for adversarial attacks against proposed 6G machine learning models for the millimeter-wave (mmWave) beam prediction using adversarial learning. The main idea behind adversarial attacks against machine learning models is to produce faulty results by manipulating trained deep learning models for 6G applications for mmWave beam prediction. We also present the adversarial learning mitigation method's performance for 6G security in mmWave beam prediction application with fast gradient sign method attack. The mean square errors (MSE) of the defended model under attack are very close to the undefended model without attack.