In the digital age of the hyper-connected Critical Infrastructures (CIs), the role of the smart electrical grid is crucial, providing several benefits, such as improved grid resilience, efficient energy distribution and smart load and response management. However, despite the several advantages, the rapid evolution of the heterogeneous technologies involved in the smart electrical grid increases the attack surface. In this paper, we focus first our attention on how Artificial Intelligence (AI) can be used to protect the smart electrical grid in terms of detecting efficiently potential cyberattacks and anomalies. Secondly, we investigate how AI can be used to trick AI-enabled detection services, thus resulting in false alarms. In particular, we emphasise on cyberattacks against IEC 60870-5-104, an industrial communication protocol which is widely used in the energy domain. Therefore, a relevant AI-powered Intrusion Detection System (IDS) is provided, utilising strong Machine Learning (ML)/Deep Learning (DL) methods, such as Decision Tree, Random Forest, XGBOOST and deep MultiLayer Perceptron (MLP). On the other hand, we investigate how adversarial attacks can affect the detection performance of the previous IDS. For this purpose, the Fast Gradient Signed Method (FGSM) is examined, and a Conditional Tabular Generative Adversarial Network (CTGAN) adversarial attack generator is implemented. The evaluation results demonstrate the efficiency of the proposed IDS and the aforementioned adversarial attacks.

The evolution of cyberattacks has been significantly impacted by the rise of Artificial Intelligence (AI). In particular, AI-driven attacks leverage Machine Learning (ML) and Deep Learning (DL) methods to automate tasks like identifying vulnerabilities, crafting convincing phishing emails, and evading conventional security measures. These cyberattacks can adapt in real time, making them more elusive and challenging to detect. Furthermore, AI has enabled the development of AI-powered malware that can learn and evolve, making it even more dangerous. As AI continues to evolve, both attackers and defenders are engaged in a relentless arms race, with cybersecurity professionals striving to harness AI for threat detection and response while cybercriminals seek to exploit AI’s capabilities for their malicious purposes. This ongoing battle underscores the need for proactive and adaptive cybersecurity strategies to mitigate the evolving threats posed by AI-driven cyberattacks. Based on the aforementioned remarks, it is evident that efficient and adaptable countermeasures are necessary. In this paper, we focus our attention on Cyber Threat Intelligence (CTI) mechanisms. CTI is the process of collecting, analysing, and sharing information about potential cybersecurity threats to help organisations proactively defend against cyberattacks. In particular, after providing an overview of the CTI use cases, a brief analysis of existing solutions follows, highlighting the current trends and directions for future work in this research field.

The new Industry 4.0 standard has offered many advantages to the industries improving their production rate since it evaluates novel cutting-edge technologies like artificial intelligence, machine learning, cyber-physical systems, and Internet of Things (IoTs) to automate manufacturing processes so as to minimize time and economical costs while improving the quality of products. However, this rapid industrial transition carries risks in terms of security and privacy issues that arise. In this article, we propose a novel secure network model to enhance network security and employees’ privacy in the edge-enabled industrial IoTs. Experimental results demonstrate encouraging performance rates in terms of accuracy, precision, recall, fall-out, F-measure, and Matthews correlation coefficient against known and unknown bot attacks.

Traffic sign recognition and autonomous vehicles computing are a few of the innovative applications which are emerging in the domain of mobile edge computing. Distributed machine learning in the form of Federated Learning (FL) has been applied to mobile edge computing through a range of methodologies and techniques for intelligent feature classification approaches. The challenges that research on such FL methods is facing is twofold: identify an optimal distributed architecture and algorithm components to each side to meet the demand of heavy data processing, and enhance the algorithm components with heuristics that fit to the problem domain and optimize the key parameters of the algorithms. In this prospect, we present a Federated Learning implementation based on a neural network architecture with emphasis to traffic sign image recognition. Our benchmark was tested with two FL strategies seeking an optimal performance model and in reference to a corresponding data set. We present the results of this work while we define the scope of future improvements to our model.

This paper introduces and describes a novel architecture scenario based on Cloud Computing and counts on the innovative model of Federated Learning. The proposed model is named Integrated Federated Model , with the acronym InFeMo . InFeMo incorporates all the existing Cloud models with a federated learning scenario, as well as other related technologies that may have integrated use with each other, offering a novel integrated scenario. In addition to this, the proposed model is motivated to deliver a more energy efficient system architecture and environment for the users, which aims to the scope of data management. Also, by applying the InFeMo the user would have less waiting time in every procedure queue. The proposed system was built on the resources made available by Cloud Service Providers (CSPs) and by using the PaaS (Platform as a Service) model, in order to be able to handle user requests better and faster. This research tries to fill a scientific gap in the field of federated Cloud systems. Thus, taking advantage of the existing scenarios of FedAvg and CO-OP, we were keen to end up with a new federated scenario that merges these two algorithms, and aiming for a more efficient model that is able to select, depending on the occasion, if it “trains” the model locally in client or globally in server.

Background All recent technological findings can be collectively used to strengthen the industrial Internet of things (IIoT) sector. The novel technology of multi-access edge computing or mobile edge computing (MEC) and digital twins have advanced rapidly in the industry. MEC is the middle layer between mobile devices and the cloud, and it provides scalability, reliability, security, efficient control, and storage of resources. Digital twins form a communication model that enhances the entire system by improving latency, overhead, and energy consumption. Methods The main focus in this study is the biggest challenges that researchers in the field of IIoT have to overcome to obtain a more efficient communication environment in terms of technology integration, efficient energy and data delivery, storage spaces, security, and real-time control and analysis. Thus, a distributed system is established in a local network, in which several functions operate. In addition, an MEC-based framework is proposed to reduce traffic and latency by merging the processing of data generated by IIoT devices at the edge of the network. The critical parts of the proposed IIoT system are evaluated by using emulation software. Results The results show that data delivery and offloading are performed more efficiently, energy consumption and processing are improved, and security, complexity, control, and reliability are enhanced. Conclusions The proposed framework and application provide authentication and integrity to end users and IoT devices.

This work initially surveys and illustrates the multiple open challenges in the field of industrial IoT-based Big Data management and analysis in Cloud environments. Challenges arise from fields of Machine Learning in the Cloud infrastructures, A.I. techniques of Big Data Analytics in the Cloud environments, and Federated Learning Cloud systems try to be clarified. Additionally, Reinforcement Learning is a novel technique that allows large data centers such as Cloud data centers to affect a more energy-efficient resource allocation. Moreover, we propose an architecture that tries to combine the features offered by several Cloud Providers to emerge and achieve an Energy-Efficient industrial IoT-based Big Data Management Framework (EEIBDM) established outside of every user, in Cloud. IoT data could be integrated with techniques such as Reinforcement and Federated Learning to achieve a Digital Twin scenario, for the virtual representation of industrial IoT-based Big Data of machines and rooms temperatures. Furthermore, we propose an algorithm for delivering the energy consumption of the infrastructure through the evaluation of the EEIBDM framework. Finally, some future directions as an expansion of our research are illustrated.

This work proposes an innovative infrastructure of secure scenario which operates in a wireless-mobile 6G network for managing big data (BD) on smart buildings (SBs). Count on the rapid growth of telecommunication field new challenges arise. Furthermore, a new type of wireless network infrastructure, the sixth generation (6G), provides all the benefits of its past versions and also improves some issues which its predecessors had. In addition, relative technologies to the telecommunications filed, such as Internet of Things, cloud computing (CC) and edge computing (EC), can operate through a 6G wireless network. Take into account all these, we propose a scenario that try to combine the functions of the Internet of Things with CC, EC and BD in order to achieve a Smart and Secure environment. The major purpose of this work is to create a novel and secure cache decision system (CDS) in a wireless network that operates over an SB, which will offer the users safer and efficient environment for browsing the Internet, sharing and managing large-scale data in the fog. This CDS consisted of two types of servers, one cloud server and one edge server. In order to come up with our proposal, we study related cache scenarios systems which are listed, presented, and compared in this work.

Cognitive Radio is a promising technology that maximize spectrum efficiency and can apply to Wireless Sensor Networks. This paper proposes a system architecture which introduces enhancements at lower layers of a Software Defined Network of Wireless Sensors Network with Cognitive Radio capabilities for efficient sensors' power management, energy consuming channel handoffs elimination, efficient spectrum brokerage, and QoS provision in terms of data rate to the sensors' applications via the SDN flows. The large Wireless Sensors Network is divided into clusters for power efficiency - as sensor operate in lower power - which connect to a cloud-assisted Central Controller. The protocol encompasses an optimal reinforcement learning scheme for efficient spectrum utilization that enables efficient sensors' data collection, while sustainability issues are satisfied. Software Defined Wireless Sensor Network dynamically adapts to the spectrum and interference conditions on per flow basis and predicts Primary Users' traffic to totally avoid collision with the licensed users. The paper is concentrated on sustainable solutions for sensors' data collection by the cluster heads leveraging the Cognitive Radio Network facilities and taking into account the demands of the applications running on the sensors. The Cognitive Radio Sensor Network is considered as large organized on a local basis to extend networks lifetime and allow resource reuse.

Today's advanced media technology preaches an enthralling time that will enormously bear on daily life. Moreover, the rapid raise of wireless communications and networking will ultimately bring advanced media to our lives anytime, anywhere, and on any device. According to the National Institute of Standards and Technology (NIST), Cloud Computing (CC) is a scheme for enabling convenient, on-demand network access to a shared pool of configurable computing pores (for example networks, applications, storage, servers, and services) which could be promptly foresighted and delivered with minimal management effort or service provider interaction. This paper proposed an efficient algorithm for advanced scalable Media-basedSmart Big Data (3D, Ultra HD) on Intelligent Cloud Computing systems. The proposed encoding algorithmoutperforms the conventional HEVC standard which demonstrated by the performance evaluations. In order to ratify the proposed approach, in addition, a relative study has been carried out. The proposed method could be used and integrated into HEVC, as a Smart Big Data, without violating the standard.

In this paper, we deal with four types of stabilization control for a remote robot system in which a user remotely operates an industrial robot arm with a force sensor by using a haptic interface device while watching video. The four types of control include the stabilization control with filters, the stabilization control by viscosity, the reaction force control upon hitting, and the switching control. To make a comparison of them quantitatively, we carry out the quality of experience (QoE) assessment in which we treat work of pushing four balls with different softness by a metal rod attached to the tip of the industrial robot arm.

The last few years, significant advances provide better solutions for interconnectivity and security in Intelligent Buildings (IBs). An overview of these advances is presented in this paper. Also, in this paper, we presented a patient monitoring system for hospital buildings and a Building Management System (BMS) layered design. Then, we made a comparative analysis of our system over other similar systems and presented the benefits that our approach has. Moreover, we proposed some security solutions that came out from the design and from further research. Also, a comparative analysis of our system over other similar systems is shown in this paper. Then, the benefits of our design are listed and explained. Finally, we have studied and used the Contiki OS and the Cooja emulator, and we have created simulations, which helped us have a more detailed and realistic image of our system. The results from the transmission of the packets of data are significant, since the protocol we use (CoAP), has a very low percentage, if not zero, of the packets, lost. Using the Cooja emulator we track the trafficc in and out of the network in real time. So, it seems to be a very useful tool which offers, except the traffic, diagrams and other metrics which describe our system. As future work, we are going to emulate our entire system with such tools like the Cooja emulator. Then, if the results are the expected, we will move on with the implementation of such a system. This paper will be a start point for better future decisions in designing intelligent building systems.

The last few years, significant advances which improve healthcare have been done in Internet of Things, in cloud computing, in video coding, and in mobile devices. This paper provides an overview of these advances. Also, we propose an IoT-based surveillance system for ubiquitous healthcare monitoring. The system consists of sensors, actuators, and cameras. Mesh topology was decided to be used as it provides important advantages. Moreover, the Constrained Application Protocol (CoAP) is used for the data compression and transferring, and the Scalable High-Efficiency Video Coding (SHVC) is used for the video compression and transferring. The SHVC can deliver the same video quality in half of the bit rate than the High-Efficiency Video Coding (HEVC). Furthermore, cloud services are provided, such as storage and real-time monitoring. Finally, we made a comparative analysis between our proposed system architecture and two other approaches. From this analysis, we can say that our system architecture has some benefits instead of other similar architectures. Also, we made an analysis of the bandwidth and the network throughput. The results are significant since the bandwidth required for the transmission of data and video is reduced.

By subjective assessment, this paper investigates the effects of group (or inter-destination) synchronization control in networked virtual environments where users have a conversation with each other by using avatars constructed by computer graphics (CG) and live voices. Assessment results show that the fairness among the users can be maintained high under the group synchronization control in networked competitive work. We also demonstrate that the synchronization quality of networked collaborative work can be improved under the group synchronization control. In addition, we make an experiment in which we use videos instead of avatars, and we examine the difference between results of the avatar case and those of the video case.

In this paper, we present an efficient method for supporting full interactive functions of MPEG-2 video streaming. The method is based on storing multiple differently encoded versions of the video stream at the server. A normal version is used for normal playback, while several other versions are used for fast/slow/jump forward (rewind)/rewind at variable speedups. Full interactive functions are produced by encoding every Nth frame of the original uncompressed movie as a sequence of I-P(M) frames. Mechanisms for controlling the interactive streams are also presented and their effectiveness is assessed through extensive simulations. Traditional interactive functions are supported with a minimum of additional resources on the server/network bandwidth and decoder complexity.