As new and upcoming technological advancements emerge, the threat of malware will continue to diversify and increase. Malware poses a serious threat to privacy and security of critical data. Some malware do not collect data but use the device's resources for crypto-mining and other activities. Thus, new technology for evading and detecting malware continues to grow and advance. Artificial Intelligence (AI) is one such field that has helped tackle this problem with great precision. Most of the existing solutions use Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and algorithms to make more accurate predictions. However, their solutions are not optimized due to generalized training and higher latency due to large model structures. Inspired by the aforementioned challenge, this paper proposes a distributed learning approach called FedShield to solve the said problem using a Windows Malware dataset. Federated Learning (FL) is one such algorithm that helps to train models distributively, ensuring data security, privacy, scalability, and diversification. Each client model has an ANN that communicates with the global model to update its model via a blockchain layer. The FL model achieves an accuracy of 96 % with 13 clients on the unseen data. Furthermore, the blockchain layer also stores the malicious files in order to make them tamper-proof and secure. The proposed FedShield system is evaluated by comparing it with pre-existing models. The transaction and execution costs in the blockchain for each function are recorded. This approach can help various anti-malware softwares to improve their products.

With the advent of technology, the transfer of sensitive information has become more prone to misuse, especially through unsecured platforms like social media. To address this challenge, UAV communication, particularly drones, has emerged as an alternative for document delivery in highly sensitive areas. But these devices can also get vulnerable to attacks which can cause a serious issue when the information is sensitive. Therefore, we propose a UAV-based secure document delivery framework that leverages AI models to detect potential attacks on the UAVs. The system ensures security throughout the document transfer process by evaluating various drone parameters. We employ the Decision Tree Classifier, which uses entropy to classify the potential threats. The result of the classification is used to guide the decision-making process for a secure delivery process. We further compare the various models based on metrics like accuracy, precision, recall, and$\mathbf{F - 1}$score, demonstrating the effectiveness of our framework, which enhances the security of UAV-based communication systems.

This article presents an optimized and decentralized resource allocation approach aimed at maximizing the system throughput and energy efficiency of device-to-device (D2D) communication. The proposed scheme modifies the meta-heuristic whale optimization algorithm (WOA) by blending the differential evolution (DE) technique in the WOA’s exploration phase to offer intelligence and reduce the computational overburden. The hybrid WOA (DE+WOA) serves as a physical layer access control that efficiently finds the optimal cellular users (CUs) and D2D users (DUs) based on their channel conditions. The proposed access control acts as a restrictive filter, where only optimal CU-DUs can participate in resource allocation tasks. Furthermore, a dataset has been prepared using the optimal CUs-DUs channel conditions from the hybrid WOA to serve as input for the federated learning (FL)-based resource allocation. We utilized statistical tests (e.g., Spearman’s test) to analyze the generated dataset’s non-independent and identically distributed (non-IID) characteristics, thus providing generalization in the AI training. Allowing only the optimal CUs and DUs (from hybrid WOA) in the FL-based resource allocation substantially reduces the computational cost of AI training and improves energy efficiency. In the FL-based resource allocation, we used a sequential convolutional neural network (CNN) trained on the aforementioned dataset to provide proactive resource allocation decisions. Furthermore, we used momentum-based weight aggregation in the FL to reduce the computational burden on the central server. The proposed scheme is assessed by utilizing different standard metrics, such as training accuracy (98.93%), training time, overall system throughput (35.62 Mbps), energy efficiency (96.42 bits/joule), and resource fairness.

Analog signal transmission has always been a crucial broadcasting technique, particularly in the early days of television. Even with the development of digital technologies, analog signals remain significant, particularly in locations remote from transmission towers. However, analog transmissions are susceptible to damage from noise and interference, which can reduce the signal-to-noise ratio (SNR). This SignalStats explores machine learning-based statistical analysis along with techniques like Adequacy Tweak (AM) and Recurrence Tweak (FM) to optimize interference control in analog stations. A multitude of factors, such as air quality, topography, and transmitter distance, influence signal quality. The project emphasizes data collection and preprocessing approaches in order to enable spatial analysis and visualization to understand station distribution and service provider dominance. Moreover, statistical analysis is used to assess the effectiveness of the signal, channel usage, and ERP. The SignalStats findings provide valuable insights for developing interference control tactics, which in turn improves the efficiency of analog communication networks in the face of rapidly changing technological environments.

This paper introduces a novel telehealth communication system, designed to enhance the security and integrity of medical data exchange. In the rapidly evolving digital healthcare landscape, the protection of sensitive patient information is paramount. To address this, our system uniquely combines quantum cryptography, specifically the BB84 protocol, with blockchain technology, offering a dual-layered security framework. The Quantum Layer, underpinned by the BB84 protocol, establishes quantum-secure communication channels, effectively encrypting data exchanges between patients, doctors, and hospitals. This layer guarantees that medical information remains confidential and safe from potential quantum-level eavesdropping threats. The subsequent Blockchain Layer further strengthens the system by storing these encrypted communications in an immutable blockchain ledger. This approach not only secures the data against unauthorized alterations but also provides a transparent and permanent record of all transactions, thereby enhancing the auditability of medical communications.

The rise of vehicular networks has ushered in the era of vehicle-to-everything (V2X) communication aimed at bolstering driving safety. A pivotal aspect of V2X communication is its role in facilitating emergency warning systems. This study focuses on the propagation of emergency messages and the provisioning of emergency services through V2X communication while considering the efficient allocation of resources necessary for effective vehicle communication. The primary objective of resource allocation within the context of Cellular-Vehicle-to-Everything (C-V2X) is to optimize the utilization of available resources, amplify system capacity, and address the diverse communication requisites within the confines of system constraints. A notable challenge in C-V2X resource allocation resides in the judicious allocation of spectrum resources and broadcast opportunities to V2X users. Therefore, we present NeuroEvolution of Augmenting Topologies (NEAT)-based efficient channel allocation within the C-V2X framework. Our approach aims to maximize the sum rate and throughput of emergency service vehicles (ESV) while ensuring the attainment of a minimum threshold throughput for other vehicles. Subsequently, we conduct a comparative analysis between the average sum rate achieved by the NEAT algorithm and a random resource allocation scheme. Furthermore, we undertake a comparative assessment of the time complexity of NEAT in contrast to other state-of-the-art techniques employed for channel allocation. These techniques encompass the graph matching algorithm, the Hungarian, and the brute force method. Our proposed C-V2X model demonstrates superior performance across various evaluation metrics compared to various alternative algorithms.

Summary In recent years, smart healthcare, artificial intelligence (AI)‐aided diagnostics, and automated surgical robots are just a few of the innovations that have emerged and gained popularity with the advent of Healthcare 4.0. Such technologies are powered by machine learning (ML) and deep learning (DL), which are preferable for disease diagnosis, identifying patterns, prescribing treatments, and forecasting diseases like stroke prediction, cancer prediction and so forth. Nevertheless, much data is needed for AI, ML, and DL‐based systems to train effectively and provide the desired outcomes. Further, it raises concerns about data privacy, security, communication overhead, regulatory compliance and so forth. Federated learning (FL) is a technology that protects data security and privacy by limiting data sharing and utilizing model information of distributed systems to enhance performance. However, existing approaches are traditionally verified on pre‐established datasets that fail to capture real‐life applicability. Therefore, this study proposes an AI‐enabled stroke prediction architecture consisting of FL based on the artificial neural network (ANN) model using data from actual stroke cases. This architecture can be implemented on healthcare‐based wearable devices (WD) for real‐time use as it is effective, precise, and computationally affordable. In order to continuously enhance the performance of the global model, the proposed FL‐based architecture aggregates the optimizer weights of many clients using a fifth‐generation (5G) communication channel. Then, the performance of the proposed FL‐based architecture is studied based on multiple parameters such as accuracy, precision, recall, bit error rate, and spectral noise. It outperforms the traditional approaches regarding accuracy, which is 5% to 10% higher.

Abstract Quantum machine learning (QML) is an emerging field that combines the power of quantum computing with machine learning (ML) techniques to solve complex problems. In recent years, QML algorithms have shown tremendous potential in various applications such as image recognition, natural language processing, health care, finance, and drug discovery. QML algorithms aim to reduce computation costs and solve complex problems beyond the scope of classical machine learning algorithms. In this article, we study the performance of two QML algorithms, that is, quantum support vector classifiers (QSVC) and variational quantum classifiers (VQC), for chronic heart disease prediction in Healthcare 4.0. The performance of the two classifiers is assessed using different evaluation metrics like accuracy, precision, recall, and F1 score. The authors concluded the superior performance of QSVC over VQC with an accuracy of 82%.

Integration of device-to-device (D2D) communication has gained significant attention within cellular networks as a means to enhance their capacity, coverage, and performance. Despite these advantages, D2D communication encounters various challenges, such as high interference, resource allocation, energy efficiency, and security. In this paper, we investigate the problem associated with resource allocation in D2D communication underlying cellular networks. The existing resource allocation schemes (e.g., game theory and graph theory) do not offer an access control mechanism, due to which the existing schemes are computationally intensive and do not converge to offer a global optimum solution. Toward this goal, we proposed a whale optimization algorithm(WOA)-based access control scheme to enhance the performance of the resource allocation scheme in D2D communication. In WOA, we created a signal-to-interference-plus-noise ratio (SINR)-based objective function that iteratively discovers the best D2D users, allowing them to participate in the resource allocation process. Moreover, for resource allocation, we adopted the Munkres algorithm, which allows only optimized D2D users (from WOA) to reuse the resources of cellular users (CUs). In the proposed work, WOA acts as an access control scheme that optimally finds the best D2D users and only allows them to reuse cellular resources in the Munkres resource assignment problem. Simulation results show that the proposed scheme significantly improves the system’s throughput compared to other existing algorithms. Moreover, other evaluation parameters, such as convergence rate, fairness, WOA update positions, and execution time, show the outperformance of the proposed scheme.

The emergence of massive automation has transformed Industrial Internet-of-Things (IIoT) to become adaptive, self-healing, and autonomous. In IloT, the increased volume of data traffic has raised questions about the privacy and security of shared sensor data, resource management, the accuracy of trained models, and the authenticity of network traffic in operation. Thus, conventional security paradigms and centralized learning models are outdated to support the IloT operational space. Modern solutions like federated learning (FL) and onion routing (OR) are integrated into IloT to secure and optimize link communication and improve the computational requirements of central model training. Thus, the paper integrates FL and OR in IloT, and presents a framework FedOnion, where federated classifiers are proposed at intermediate OR circuits, which preserves anonymity and privacy of data sharing among nodes in IloT. In this frame-work, an FL-assisted network traffic classification approach is presented for malicious or non-malicious data requests forwarded to the OR network. Malicious requests are discarded at the next onion router, and it prevents the shared key from getting compromised, as the hash is computed at each hop to signify that data is not tampered with. FL-classifiers divide the overall dataset into small segments, which alleviates the computational burden on OR links and improves the detection rate of malicious data requests. The proposed framework's effectiveness is demonstrated on real-world IloT datasets, based on security and computational parameters. The obtained results indicate the practical viability of the scheme for critical industrial setups which paves the way towards a robust and secured industrial future. The proposed framework is assessed using different performance parameters, such as FL MSE$(10^{-9}$at 300 epochs), onion circuit compromisation rate (16%), and 5G modulation scheme.

With the tremendous emergence of the Industrial Internet of Things (IIoTs) in varied industrial sectors, software-defined networking (SDN) has become a prominent paradigm to improve the scalability, latency, and response time of large-scale IIoT networks. However, despite the enhanced network performance of the IIoT networks, efficient and optimal load balancing and distribution is still one of the critical aspects of the SDN paradigm that can overburden the controllers further degrading the system performance. To address the aforementioned issue, we have utilized the game theory approach to enable the distributed, optimal, and efficient load balancing among multiple SDN controllers considering the IIoT systems over a 5G communication network. The proposed approach focuses on balancing the load state, i.e., idle or medium loaded, of the controllers with the help of employed coalition game theory to evenly and optimally distribute the load between controllers by providing them incentives fairly. For that, we have determined two Nash equilibrium using formulated strategies based on the load state of the controllers. Finally, the proposed game theory approach for load balancing is evaluated, considering various performance metrics such as overall convergence utility, packet error rate, and fairness.

Fifth-generation (5G) offers more advanced and promising wireless communication technology as Device-to-device (D2D) communication. It refers to the direct data exchange between two users' equipment in a wireless network without routing their data through the base station. The close proximity of the devices offers a higher data rate with low communication latency and increases spectral efficiency. Despite the advantages mentioned above, there are still some challenges, such as interference, power control, and security, that need to be addressed concerning D2D communication. There exist many game theory-based solutions for efficient resource allocation. However, they face issues when there are many users in the communication environment. Hence, we proposed artificial intelligence (AI) and game theory-based solutions for efficient resource allocation in this paper. Initially, we proposed different machine learning (ML) classifiers, such as isolation forest (IF), support vector machine (SVM), gradient boosting (GB) classifier, K-nearest neighbours (KNN), and Gaussian naive Bayes (GNB) that select best D2D users. Then, we formulate a coalition game that gives efficiently allocates resources to the best-selected D2D users. Further, we considered different performance evaluation parameters, such as accuracy, validation loss, sum rate, and convergence rate. The empirical results represent that the GB classifier achieves the highest accuracy, 98.23%, because it trains faster with the large dataset size, and the coalition game-based approach maximizes the overall system sum rate for efficient resource allocation in D2D communication.

M2M communication in the Industrial Internet of Things is still in its infancy as the information exchange between machines is hindered by various modern security challenges and threats. An attacker can leverage the M2M communication by exploiting it with resource exhaustion, data integrity, and injection attacks. In this article, to address the aforementioned security issues, we first employed a long short-term memory based AI model on the edge servers to classify the machines' malicious and nonmalicious message requests and forwarded them to the onion routing (OR) network. Then, to enhance the security and reliability of the conventional OR network, we have associated it with blockchain technology by incorporating two additional fields along with the original message requests, i.e., verifying token and time to live that validates the incoming message requests. Additionally, the OR network, along with blockchain, is simulated inside a discrete simulator, i.e., a shadow simulator. Finally, the performance of the proposed system is evaluated with different performance metrics, such as F1 score, precision, recall, and false-negative rate. The empirical results show that the proposed OR network outperforms the conventional OR in terms of throughput, decryption time (computationally inexpensive), and OR circuit compromised rate.

The advancement in technology has brought to life the concept of Autonomous vehicles (AV). The primary goal of AV is to reduce driving stress and provide comfort to the occupants. Since AVs can drive themselves, it poses a question of passenger security. Furthermore, AVs are connected to an open network like a public Internet to communicate to the outer world, raising security and privacy concerns. Skillful attackers can effortlessly infiltrate the vehicle by injecting malware which can disrupt the regular operation of the entire AV system. A Deep Learning (DL) and Blockchain framework is proposed for AV to resolve the aforementioned security challenges. The network traffic is continuously monitored, and the malware binaries are converted to grey-scale images, which are then classified by Convolutional Neural Network (CNN) employed in the DL model. The CNN architecture, ResNet50V2, has been tested and proves to be efficient in detecting malware with an accuracy of 97.56%.

Sensor communication in the smart home environment is still in its infancy as the information exchange between sensors is vulnerable to security threats. Many traditional solutions use single-layer or multi-layer (i.e., onion routing protocol) encryption/decryption algorithms. But, in the traditional onion routing protocol, if the directory server is compromised, it may not track the malicious onion nodes within the onion network. It questioned the path anonymity of the onion routing protocol. Motivated by this, we proposed a blockchain and onion routing (OR)-based secure and trusted framework in the paper. The anonymity of the proposed OR network is maintained by storing and tracking the onion nodes threshold values through the blockchain network. A long short-term memory (LSTM) model is also utilized to classify the sensors data requests as malicious and non-malicious. The performance of the proposed system is evaluated with different performance metrics such as F1 score and accuracy. The LSTM model significantly improves the initial detection rate of malicious data requests from smart home sensors. Over these benefits, we considered the entire communication via 6G channel, reducing the overall communication latency. Additionally, the OR network is simulated over the shadow simulator to analyze the OR network’s performance considering parameters such as packet delivery ratio and malicious onion node detection rate.