Federated Learning (FL) emerged as a significant advancement in the field of Artificial Intelligence (AI), enabling collaborative model training across distributed devices while maintaining data privacy. As the importance of FL and its application in various areas increased, addressing trustworthiness issues in its various aspects became crucial. In this survey, we provided a comprehensive overview of the state-of-the-art research on Trustworthy FL, exploring existing solutions and key foundations relevant to Trustworthiness in FL. There has been significant growth in the literature on trustworthy centralized Machine Learning (ML) and Deep Learning (DL). However, there is still a need for more focused efforts toward identifying trustworthiness pillars and evaluation metrics in FL. In this paper, we proposed a taxonomy encompassing five main classifications for Trustworthy FL, including Interpretability and Explainability, Transparency, Privacy and Robustness, Fairness, and Accountability. Each category represents a dimension of trust and is further broken down into different sub-categories. Moreover, we addressed trustworthiness in a Decentralized FL (DFL) setting. Communication efficiency is essential for ensuring Trustworthy FL. This paper also highlights the significance of communication efficiency within various Trustworthy FL pillars and investigates existing research on communication-efficient techniques across these pillars. Our survey comprehensively addresses trustworthiness challenges across all aspects within the Trustworthy FL settings. We also proposed a comprehensive architecture for Trustworthy FL, detailing the fundamental principles underlying the concept, and provided an in-depth analysis of trust assessment mechanisms. In conclusion, we identified key research challenges related to every aspect of Trustworthy FL and suggested future research directions. This comprehensive survey served as a valuable resource for researchers and practitioners working on the development and implementation of Trustworthy FL systems, contributing to a more secure and reliable AI landscape.

Organizational cybersecurity relies heavily on security operation centers (SOCs) to protect businesses and institutions from emerging cyber threats. In recent years, the complexity and sophistication of cyber threats have increased, pushing SOCs to their limits. As a result, SOCs struggle to address the evolving threat landscape due to their reliance on isolation technologies and reactive strategies. However, advanced technologies, such as artificial intelligence (AI) and machine learning (ML), have the potential to revolutionize SOCs by enhancing threat identification and response capabilities, as well as predicting and preempting risks. To address these challenges and highlight the full potential of SOC, this study provides a detailed overview through a comprehensive literature review that identifies gaps in existing research and examines the latest technologies used in the SOC environment to help address different operational and technical challenges and bring out their capabilities. Various methods, ranging from automated incident response and behavioral analytics to neural networks and deep learning, have been classified and compared. In addition, an in-depth reference architectural model, which is a blueprint for SOC integrating AI and ML into SOCs, is introduced. The proposed model provides a structured framework for implementation and offers insights into different SOC components and their interactions. Moreover, this systematic review emphasizes the benefits of these technologies for enhancing security operations. Finally, a case study is presented to describe the function of ML-and AI-powered SOC components to achieve optimum security. This paper concludes by discussing additional challenges and future research directions that may help advance the cybersecurity sector and provide insights into improving SOCs.

Cyber-physical systems (CPS) are recognized for their intelligence as they seamlessly interact with humans, enhancing the physical world through computation, communication, and control. Over the last few years, the evolution of CPS, including IoT components, has significantly impacted many facets of people’s lifestyles. It has been immersed in a wide range of services and applications in various areas, including manufacturing, healthcare, and energy. However, the interrelationship between the cyber and physical worlds gives rise to a multitude of research problems and challenges. In the healthcare field, for instance, CPS introduces complexities related to interoperability, privacy, data security, and real-time data processing with critical implications for the reliability and safety of medical processes. To address these challenges and harness the full potential of CPS in healthcare, this paper, through a comprehensive literature review, aims to discuss cutting-edge CPS technologies and solutions that hold promise for healthcare applications. To this end, we propose a comprehensive architectural model that can serve as a benchmark for implementing CPS in healthcare applications. This model thoroughly details how services, components, and technologies can be integrated to transform massive raw data collected from the physical world into valuable information for an enhanced decision-making process. Finally, a use case on healthcare CPS is presented, outlining its characteristics, the role that different technologies have played in its development, and the major challenges in implementing such systems successfully. This study provides a cohesive understanding of the role CPS can play in empowering healthcare while offering insights into the challenges, and future research trends.

Wireless body area networks (WBANs) have emerged as a promising solution for addressing challenges faced by elderly individuals, limited medical facilities, and various chronic medical conditions. WBANs consist of wearable sensing and computing devices interconnected through wireless communication channels, enabling the collection and transmission of vital physiological data. However, the energy constraints of the battery-powered sensor nodes in WBANs pose a significant challenge to ensuring long-term operational efficiency. Two-hop routing protocols have been suggested to extend the stability period and maximize the network’s lifetime. These protocols select appropriate parent nodes or forwarders with a maximum of two hops to relay data from sensor nodes to the sink. While numerous energy-efficient routing solutions have been proposed for WBANs, reliability has often been overlooked. Our paper introduces an energy-efficient routing protocol called a Hybrid Clustering Approach for Extending WBAN Lifetime (HCEL) to address these limitations. HCEL leverages a utility function to select parent nodes based on residual energy (RE), proximity to the sink node, and the received signal strength indicator (RSSI). The parent node selection process also incorporates an energy threshold value and a constrained number of serving nodes. The main goal is to extend the overall lifetime of all nodes within the network. Through extensive simulations, the study shows that HCEL outperforms both Stable Increased Throughput Multihop Protocol for Link Efficiency (SIMPLE) and Energy-Efficient Reliable Routing Scheme (ERRS) protocols in several key performance metrics. The specific findings of our article highlight the superior performance of HCEL in terms of increased network stability, extended network lifetime, reduced energy consumption, improved data throughput, minimized delays, and improved link reliability.

Wireless Body Area networks (WBANs) have been adopted extensively in academic and industrial research and development in recent years. WBANs promise to provide a suitable environment for remote patient monitoring and enable caregivers to intervene in case of abnormal health conditions. However, WBANs sensors are resource-constrained and face challenges, including, for instance, sensor energy harvesting, efficient routing, parent node selection in case of two hubs links, and data security. The stringent healthcare requirements burden managing WBAN resources and sensor functionality. In this research work, we tackle the issue of total energy consumption, communication overhead, and the lifespan of WBAN. We study the effect of routing and parent node selection on the network lifespan. The study considers a cluster-based routing protocol to establish a WBAN. This approach divides the network into clusters, where each cluster consists of a cluster head called a Relay Node (RN) and a set of functional sensors. Each RN collects data from its sensor nodes and sends it to a base station. However, the relay nodes are susceptible to failures at any time due to the challenging deployment environments and resource constraints of the nodes. In addition, the network sensors are dynamic in positions due to user body movements. Therefore, improving the robustness, fault management, and reliability at different postures becomes necessary. We propose a mobility-aware, energy-efficient Hybrid Fault-Management Clustering Algorithm (HFMCA) adopting the Weighted Bipartite Graph (WBG) to handle the vulnerable RNs prone to failure. The WBG helps find the optimum path between the vulnerable RN and its members to the sink node while maintaining minimum energy consumption and transmission costs. Finally, we conducted extensive experiments, and the simulation results illustrate the proposed algorithm’s efficiency in WBANs regarding energy consumption, network lifespan, and communication overhead.

Recent developments in sensors, wireless communications, and data processing technologies are the main drivers for adopting the Internet of Things (IoT) in healthcare systems. IoT-based healthcare systems can enhance the quality of life significantly and help prevent the occurrence of health problems and epidemics. Deploying IoT-based healthcare on a massive scale raises several issues and challenges. One of the main challenges is the management of the end-to-end network connections of the IoT-based healthcare system. This paper presents a comprehensive survey of smart network management protocols that improve IoT-based healthcare efficiency, ensuring real-time monitoring, secure data transmission, and effective device management. Moreover, a reference architecture has been proposed for the network management of IoT-based smart healthcare systems to ensure the sustainability of service delivery to patients and caregivers. The architecture avoids health-related risks and anomalies by incorporating proper network management techniques and operational requirements pertaining to smart healthcare systems. This paper also discusses architectural implementation insights supported by new technologies such as software-defined networking (SDN) and deep learning (DL). Finally, this paper explores emerging paradigms to advance next-generation network management protocols for future smart healthcare systems.