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.

As sixth-generation (6G) networks continue to evolve, the deployment of Machine Learning (ML) models in critical functions, such as millimeter-wave (mmWave) beam prediction, presents unique security challenges, particularly from adversarial attacks. Existing defenses against these attacks often have limitations, especially when gradient information is unavailable. This paper introduces the Lemur Optimizer for Adversarial Attacks (LO-Attack), a novel gradient-free approach inspired by swarm intelligence to enhance the robustness of 6G beam prediction models. By integrating LO-Attack into the adversarial training process, models become more resilient against both gradient-based and gradient-free attacks in dynamic, high-mobility environments. Experimental results from two 6G scenarios, encompassing indoor and outdoor settings, demonstrate that models trained with LOAttack achieve significant improvements in accuracy, resistance to adversarial perturbations, and computational efficiency. On average, adversarial training with LO-Attack enhances model robustness by 57.90%, outperforming traditional FGSM-based methods. These findings highlight LO-Attack's potential as an effective and scalable defense strategy for securing ML-driven applications in the complex 6G landscape.

This paper presents a new framework that integrates Federated Learning (FL) with advanced privacy-preserving mechanisms to enhance the security of millimeter-wave (mmWave) beam prediction systems in 6G networks. By decentralizing model training, the framework safeguards sensitive user information while maintaining high model accuracy, effectively addressing privacy concerns inherent in centralized Machine learning (ML) methods. Adaptive noise augmentation and differential privacy principles are incorporated to mitigate vulnerabilities in FL systems, providing a robust defense against adversarial threats such as the Fast Gradient Sign Method (FGSM). Extensive experiments across diverse scenarios, including adversarial attacks, outdoor environments, and indoor settings, demonstrate a significant 17.45% average improvement in defense effectiveness, underscoring the framework’s ability to ensure data integrity, privacy, and performance reliability in dynamic 6G environments. By seamlessly integrating privacy protection with resilience against adversarial attacks, the proposed solution offers a comprehensive and scalable approach to secure mmWave communication systems. This work establishes a critical foundation for advancing secure 6G networks and sets a benchmark for future research in decentralized, privacy-aware machine learning systems.

This paper examines the security challenges while implementing Machine Learning (ML) algorithms to Sixth Generation (6G) networks, specifically in Millimeter-Wave (mmWave) beam prediction. While ML has significant benefits, the potential vulnerabilities of Artificial Intelligence (AI) models to adversarial attacks remain a concern. To mitigate these risks, a new Integrated Transformer and Feedforward Model (ITFM) has been introduced, which accomplishes real-time beamforming vector prediction and adversarial defense. This approach enhances the reliability and security of 6G applications. The proposed model demonstrated a 37.86% average increase in defense effectiveness against adversarial threats in indoor and outdoor scenarios.

The rapid evolution of 6G networks has brought novel security and privacy challenges in managing user data, particularly with the extensive use of millimeter wave communications (mmWave) technology. Ensuring robust security and privacy preservation in this dynamic network environment is paramount. This paper explores a multifaceted approach to address these challenges, focusing on Federated Learning (FL) for mmWave beam prediction and utilizing outlier detection in the aggregation process to mitigate adversarial attacks like the Fast Gradient Sign Method (FGSM). The potential of FL to enhance beam prediction accuracy while safeguarding user data privacy is investigated by training models on edge devices and aggregating model updates rather than raw data. Furthermore, integrating outlier detection in the aggregation process identifies and filters malicious model up-dates that may compromise the FL system's integrity. Simulations assessing the robustness of the proposed system against various threats reveal substantial enhancement in data security, with an average 15.30% increase in defense effectiveness.

With the increasing popularity of Cyber-physical Systems (CPS), there is a growing need for efficient and reliable methods for detecting and responding to threats. Federated Learning (FL) is a distributed Machine Learning (ML) technique that can be used to train models on data from multiple devices (i.e., edge devices) while keeping the data local. FL has the potential to improve the security and privacy of data while also reducing the training time and cost. Particularly, CNN-based FL has been shown to be effective for various tasks such as image classification and object detection. However, selecting suitable hyperparameters for constructing local ML models in FL is a significant challenge for practical inference and training on edge devices. In this paper, we focus on the optimization of CNN-based federated learning for the task of cyber-physical detection and we propose employing a novel metaheuristic optimization algorithm called Honey Badger Algorithm (HBA) for tuning the hyperparameters in local ML models (FL-HBA). To show the effectiveness of FL-HBA, we make an evaluation using an intelligent healthcare case study where we consider Sleep Apnea (SA) and use the PhysioNet apnea ECG dataset to diagnose SA. Our results show that the FL-HBA is superior to a Convolutional Neural Network (CNN) baseline, traditional ML techniques, and centralized learning models. Furthermore, we demonstrate that the proposed method for assigning the near-optimal hyperparameter values for centralized learning models improves accuracy by 2%.

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].

The increasing number of applications and devices in the Sixth-generation (6G) networks and the diversity of mobile data, architectures, and technologies make security and privacy a critical concern. Advanced metaheuristics algorithms (MHAs) have recently become a viable solution for optimizing security and privacy in wireless networks, combining game theory and convex optimization, and several other advanced models. As a subfield of Artificial Intelligence (AI), MHAs are inspired by concepts from Evolutionary Algorithms (EAs), Trajectory-based Algorithms (TAs), and Swarm Intelligence (SI). Recent implementations of MHAs in the 6G networks have effectively solved complex security and privacy problems. This study examines MHAs’ utilization in addressing security and privacy challenges in 6G networks. The paper provides a comprehensive overview of MHAs and their use in solving security and privacy problems in 6G. The current limitations of the literature are also identified, and avenues for further research are suggested. The reader will have a clear image of the needed technologies and tools for securing 6G networks using MHAs.

Federated Learning (FL) is a type of Machine Learning (ML) technique in which only learned models are stored on a server to sustain data security. The approach does not gather server-side data but rather directly shares only the models from scattered clients. Due to the fact that clients of FL frequently have restricted connection bandwidth, it is necessary to optimize the communication between servers and clients. FL clients frequently interact through Wi-Fi and must operate in uncertain network situations. Nevertheless, the enormous number of weights transmitted and received by existing FL aggregation techniques dramatically degrade the accuracy in unstable network situations. We propose a federated GWO (FedGWO) algorithm to reduce data communications. The proposed approach improves the performance under unstable network conditions by transferring score principles rather than all client models' weights. We achieve a 13.55% average improvement in the global model's accuracy while decreasing the data capacity required for network communication. Moreover, we show that FedGWO achieves a 5% reduction in accuracy loss compared to FedAvg and Federated Particle Swarm Optimization (FedPSO) methods when tested on unstable networks.

COVID-19 is the disease evoked by a new breed of coronavirus called the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Recently, COVID-19 has become a pandemic by infecting more than 152 million people in over 216 countries and territories. The exponential increase in the number of infections has rendered traditional diagnosis techniques inefficient. Therefore, many researchers have developed several intelligent techniques, such as deep learning (DL) and machine learning (ML), which can assist the healthcare sector in providing quick and precise COVID-19 diagnosis. Therefore, this paper provides a comprehensive review of the most recent DL and ML techniques for COVID-19 diagnosis. The studies are published from December 2019 until April 2021. In general, this paper includes more than 200 studies that have been carefully selected from several publishers, such as IEEE, Springer and Elsevier. We classify the research tracks into two categories: DL and ML and present COVID-19 public datasets established and extracted from different countries. The measures used to evaluate diagnosis methods are comparatively analysed and proper discussion is provided. In conclusion, for COVID-19 diagnosing and outbreak prediction, SVM is the most widely used machine learning mechanism, and CNN is the most widely used deep learning mechanism. Accuracy, sensitivity, and specificity are the most widely used measurements in previous studies. Finally, this review paper will guide the research community on the upcoming development of machine learning for COVID-19 and inspire their works for future development. This review paper will guide the research community on the upcoming development of ML and DL for COVID-19 and inspire their works for future development.