The authors propose an agile, softwarized infrastructure for the flexible, cost-effective, secure, and privacy-preserving deployment of Internet of Things systems for smart healthcare applications and services.

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.

Performance Evaluation of IEEE 802.15.4: Experimental and Simulation Results

Modern information technology services largely depend on cloud infrastructures to provide their services. These cloud infrastructures are built on top of Datacenter Networks (DCNs) constructed with high-speed links, fast switching gear, and redundancy to offer better flexibility and resiliency. In this environment, network traffic includes long-lived (elephant) and short-lived (mice) flows with partitioned/aggregated traffic patterns. Although SDN-based approaches can efficiently allocate networking resources for such flows, the overhead due to network reconfiguration can be significant. With limited capacity of Ternary Content-Addressable Memory (TCAM) deployed in an OpenFlow enabled switch, it is crucial to determine which forwarding rules should remain in the flow table and which rules should be processed by the SDN controller in case of a table-miss on the SDN switch. This is needed in order to obtain the flow entries that satisfy the goal of reducing the long-term control plane overhead introduced between the controller and the switches. To achieve this goal, we propose a machine learning technique that utilizes two variations of Reinforcement Learning (RL) algorithms—the first of which is a traditional RL-based algorithm, while the other is deep reinforcement learning-based. Emulation results using the RL algorithm show around 60% improvement in reducing the long-term control plane overhead and around 14% improvement in the table-hit ratio compared to the Multiple Bloom Filters (MBF) method, given a fixed size flow table of 4KB.