Mitigating Security Risks in 6G Networks-Based Optimization of Deep Learning

The rapid development of 6G millimeter-wave (mmWave) networks has introduced new challenges for network security. Adversarial attacks on beamforming algorithms in these networks can lead to severe communication performance degradation. This paper proposes an optimization framework for Deep Learning (DL) hyperparameters that enhances adversarial security in 6G mmWave networks through beam prediction. We develop a robust DL model that can adapt to various adversarial attacks and maintain high prediction accuracy. The proposed framework optimizes hyperparameters using hybrid Particle Swarm Optimization (PSO) with Multi-Verse Optimizer (MVO) for improved security. The framework is evaluated through extensive simulations, demonstrating its effectiveness in improving network security and robustness against adversarial attacks. Under normal conditions, the optimized model achieves the lowest mean squared error (MSE) of 9.4410E - 05 for beamforming codeword predictions. Subjected to Fast Gradient Sign Method (FGSM) adversarial attacks, the optimized model maintains the lowest MSE of 2.2910E - 03, indicating greater resilience against adversarial perturbations. With adversarial training, the optimized model achieves the lowest MSE of 2.7110E - 03, demonstrating the most robust defense against adversarial attacks. In contrast, the non-optimized model suffers significant performance degradation under adversarial and defended conditions. The source code is available at [1].