The rapid expansion of IoT ecosystems introduces severe challenges in scalability, security, and real-time decision-making. Traditional centralized architectures struggle with latency, privacy concerns, and excessive resource consumption, making them unsuitable for modern large-scale IoT deployments. This paper presents a novel Federated Learning-driven Large Language Model (FL-LLM) framework, designed to enhance IoT system intelligence while ensuring data privacy and computational efficiency. The framework integrates Generative IoT (GIoT) models with a Gradient Sensing Federated Strategy (GSFS), dynamically optimizing model updates based on real-time network conditions. By leveraging a hybrid edge-cloud processing architecture, our approach balances intelligence, scalability, and security in distributed IoT environments. Evaluations on the IoT-23 dataset demonstrate that our framework improves model accuracy, reduces response latency, and enhances energy efficiency, outperforming traditional FL techniques (i.e., FedAvg, FedOpt). These findings highlight the potential of integrating LLM-powered federated learning into large-scale IoT ecosystems, paving the way for more secure, scalable, and adaptive IoT management solutions.

The proliferation of connected vehicles within the Internet of Vehicles (IoV) ecosystem presents critical challenges in ensuring scalable, real-time, and privacy-preserving traffic management. Existing centralized IoV solutions often suffer from high latency, limited scalability, and reliance on proprietary Artificial Intelligence (AI) models, creating significant barriers to widespread deployment, particularly in dynamic and privacy-sensitive environments. Meanwhile, integrating Large Language Models (LLMs) in vehicular systems remains underexplored, particularly in terms of prompt optimization and effective utilization in federated contexts. To address these challenges, we propose the Federated Prompt-Optimized Traffic Transformer (FPoTT), a novel framework that leverages open-source LLMs for predictive IoV management. FPoTT introduces a dynamic prompt optimization mechanism that iteratively refines textual prompts to enhance trajectory prediction. The architecture employs a dual-layer federated learning paradigm, combining lightweight edge models for real-time inference with cloud-based LLMs to retain global intelligence. A Transformer-driven synthetic data generator is incorporated to augment training with diverse, high-fidelity traffic scenarios in the Next Generation Simulation (NGSIM) format. Extensive evaluations demonstrate that FPoTT, utilizing EleutherAI Pythia-1B, achieves 99.86% prediction accuracy on real-world data while maintaining high performance on synthetic datasets. These results highlight the potential of open-source LLMs in facilitating secure, adaptive, and scalable IoV management, providing a promising alternative to proprietary solutions in smart mobility ecosystems.

With the rapid digitalization of healthcare systems, there has been a substantial increase in the generation and sharing of private health data. Safeguarding patient information is essential for maintaining consumer trust and ensuring compliance with legal data protection regulations. Machine learning is critical in healthcare, supporting personalized treatment, early disease detection, predictive analytics, image interpretation, drug discovery, efficient operations, and patient monitoring. It enhances decision-making, accelerates research, reduces errors, and improves patient outcomes. In this paper, we utilize machine learning methodologies, including differential privacy and federated learning, to develop privacy-preserving models that enable healthcare stakeholders to extract insights without compromising individual privacy. Differential privacy introduces noise to data to guarantee statistical privacy, while federated learning enables collaborative model training across decentralized datasets. We explore applying these technologies to Heart Disease Data, demonstrating how they preserve privacy while delivering valuable insights and comprehensive analysis. Our results show that using a federated learning model with differential privacy achieved a test accuracy of 85%, ensuring patient data remained secure and private throughout the process.

The Internet of Medical Things (IoMT) plays a pivotal role in healthcare, connecting a myriad of medical devices and applications for efficient patient care. However, the rising prevalence of cyberattacks targeting healthcare institutions for patient data underscores the critical need for robust security measures. This paper introduces a novel Homogenous Collaborative Machine Learning (HCML)-based model to enhance the security of healthcare-connected devices. Utilizing a Deep Neural Network (DNN) algorithm, our model constructs a tailored security framework by integrating multiple device ’edges’, enhancing the system’s ability to thwart cyber threats. We investigate the impact of incorporating additional edges on the model’s performance, employing various metrics and assessing execution times with the IoT healthcare security dataset. Our findings reveal that, compared to conventional centralized learning methods, our proposed HCML model achieves superior generalization, incremental learning, and performance enhancement while maintaining stringent data privacy. This research contributes significantly to the IoMT field by providing a scalable and robust security solution adaptable to the evolving landscape of cyber threats.

The growing number of Internet of Things (IoT) applications and connected devices has increased the chance for more cyberattacks against those applications and devices and emphasized the need to protect the IoT networks. Due to the vast network and the anonymity of the internet, it has been challenging to preserve private information and communication. Although most systems implement security devices (i.e. firewalls) to avoid this, the second line of defence, Intrusion Detection Systems (IDSs), are critical in enhancing the system's security level. This paper proposed a model that combines the two machine learning techniques, Federated and Transfer Learning, to build an IDS to secure the IoT networks with less training time and enhanced performance while preserving the user's data privacy. Deep learning algorithms, namely Deep Neural Network (DNN) and Convolutional Neural Network (CNN), are used to evaluate the performance of the proposed framework on a benchmark dataset, CSE-CIC-IDS2018, and the feasibility of adopting Federated Transfer Learning (FTL) is shown in terms of performance metrics and training and fine-tuning time. The results show that the proposed technique can increase performance and decrease training time compared to the traditional machine learning techniques.

The Internet of Vehicles (IoV) is a set of connected vehicles supported with sensors, communication technologies, and software connected by the Internet as an infrastructure. With the evolution of 5G technology, automation, and artificial intelligence, the IoV is expected to replace traditional transportation systems in the near future. On the other hand, with this evolution, the possibility of new cyberattacks has increased. This paper proposes a security framework in which intrusion detection secures the Intra/Inter-Vehicular communications within the IoV network. The proposed framework uses multi-task trans-fer learning to transfer knowledge gained from two different benchmark datasets. To the best of our knowledge, this is the first work that uses transfer learning to transfer the knowledge between two different benchmark datasets. The performance of the intrusion detection engine is evaluated using two different deep learning algorithms, namely Deep Neural Network (DNN) and Convolutional Neural Network (CNN), in terms of accuracy, precision, recall and F1-score. In addition to achieving satisfying performance and reduced training/fine-tuning time for the target domains, our analysis illustrates the computational effectiveness of the proposed model by transferring the knowledge from the smaller to the larger dataset.

The extensive growth of the Internet of Things (IoT) has impacted diverse applications, including smart homes and cities, Intelligent Transport Systems (ITS) and smart factories. IoT integrates billions of smart devices -predicted to increase from 27 billion in 2017 to 125 billion by 2030- and manages communication between them. This degree of expanded connectivity requires extensive further analysis with respect to security, and the involvement of millions of factors and users increases vulnerability in IoT environments. However, Deep Learning (DL) approaches, which originated from machine learning (ML), have been efficient in many research fields, and current studies show the effectiveness of DL for IoT security applications. In this paper, we present detailed analyses of IoT security requirements and challenges, discuss the specific role of DL and review state-of-art research work in IoT environments using DL approaches. We also performed comparative analysis of DL algorithms such as RNN, LSTM, CNN, DBN and AE. And finally, we identified research issues in the current investigations, and outlined the future directions of DL algorithms in IoT security domains.