Despite its advantages for privacy-preserving data-driven modeling, federated learning is vulnerable to privacy breaches, as demonstrated by recent attacks on its privacy properties. It has been proven that sharing the weights alone is insufficient to protect the underlying data. In this work, we provide a solution for sharing the aggregated weights with a central server while safeguarding the privacy of individual client weights. Our solution introduces a decentralized committee election mechanism, eliminating the need for a trusted party. The election phase is based on verifiable random functions (VRFs), whereas the aggregation phase is based on Elliptic curve cryptography and multi-party secret-sharing schemes. Our experimental results show that our solution outperforms the proposed solutions in terms of communication and computation costs. Overall, our approach offers a robust solution for privacy-preserving federated learning without compromising its accuracy and without relying on a third party.

Graph neural networks (GNNs) have recently garnered significant attention for use in network intrusion detection systems (NIDS), owing to their ability to model network traffic as graphs and capture complex dependencies between flows. However, existing GNN-based methods face critical limitations: their reliance on labeled data, often scarce or noisy in practice, and their inability to address multi-scale threats, such as localized node anomalies (e.g., port scanning), coordinated subnet-work attacks (e.g., botnets), and global network-wide campaigns (e.g., DDoS attacks). To bridge this gap, we propose Multi-Scale Graph Contrastive Representation Learning (MGCRL), a semi-supervised framework that hierarchically integrates three perspectives to model network intrusions. At the node level, MGCRL constructs semantic subnetworks around individual traffic flows to capture fine-grained behavioral deviations. For subnetwork-level threats, it employs substructure-aware pooling to identify coordinated anomalies, such as clusters of devices exhibiting synchronized malicious activity. Finally, at the global level, MGCRL derives representations that reflect the holistic state of the network, enabling detection of large-scale threats, such as distributed malware propagation. MGCRL couples a shared GNN encoder with a multi-level contrastive loss to align multi-scale representations while largely eliminating label dependence. It learns discriminative features from unlabeled traffic, sharpens decision boundaries with minimal supervision, and exposes anomalies that surface in a hierarchical network context by contrasting related and unrelated nodes at each scale. Extensive experiments on three benchmark datasets for multi-class classification show that MGCRL consistently outperforms SOTA methods, particularly under severe label scarcity and class imbalance.

This paper presents FFS-ORAN-IDS, a federated few-shot intrusion-detection framework that secures streaming traffic in Open Radio Access Networks (O-RAN) while respecting their stringent latency and resource constraints. The framework addresses the twin challenges of scarce attack labels and heterogeneous data, where naïve pseudo-label injection without sufficient confidence propagates errors, large-scale labeling of streaming traffic is impractical, and inherent uncertainty often requires costly human intervention. FFS-ORAN-IDS combines three coordinated x-functional blocks: a confidence-adaptive curriculum that releases pseudo-labels only when local TabTransformers are reliable, a diversity filter that retains the most informative uncertain packets, and a token-budgeted large-language-model (LLM) oracle that verifies the remaining hard samples. A mixed-integer optimization jointly governs curriculum pacing, sampling size, and Oracle LLM calls so that each federated round minimizes detection loss, propagation error, and LLM token cost under per-round resource caps. We train FFS-ORAN-IDS in two stages: an initial few-shot phase that fits the TabTransformer on the scarce ground-truth packets, followed by iterative rounds that refine the model with oracle-verified pseudo-labels. Experimental evaluation on the CIC-IDS 2018 benchmark shows that the proposed framework improves detection accuracy by 6%, reduces label-error propagation by 20%, and lowers energy consumption by 40% in the most label-constrained scenarios.

Deploying transformer models in Personalized Federated Learning (PFL) over wireless networks is challenging due to their large size, which leads to high communication overhead, increased latency, and excessive energy consumption. Traditional pruning and sparsification methods, designed mainly for conventional deep learning architectures, are ineffective for transformers and can cause divergence or degrade performance—especially when applied to self-attention layers or through direct federated averaging. To address these challenges, we propose a novel dual approach called PFL-TPS (PFL with Transformer Pruning and Sparsification). Our approach efficiently reduces communication and computation costs while maintaining model performance, making it suitable for resource-constrained wireless networks. Specifically, we apply adaptive pruning with trainable thresholds to the transformer's Feed-Forward Layers (FFLs), and only these trainable thresholds are shared with the server, resulting in minimal uploaded data. For the Self-Attention Layers (SALs), instead of transmitting bandwidth-intensive model parameters, we employ a server-side hypernetwork that generates personalized parameters based on device-specific embedding vectors sent by the devices, significantly reducing communication overhead and maintaining personalization. Extensive experiments show that PFL-TPS reduces energy consumption by up to 50%, decreases training time by 60.44%, and improves model accuracy by 49.87% compared to baselines in wireless networks.

Spatiotemporal graph neural networks (STGNNs) have proven especially effective in traffic prediction tasks by modeling sensors or regions as nodes, with distances and correlations as edges. Their ability to capture complex spatiotemporal dependencies in road networks drives key applications in public safety, urban planning, and intelligent transportation. However, existing STGNNs often rely on manually designed architectures and typically process multiview graphs separately, requiring specialized expertise, thus limiting flexibility and overlooking intricate spatiotemporal interdependencies. To address these challenges, we propose an Attention-based Dynamic Multiview Spatiotemporal Graph Neural Architecture Search (ADMGNAS) framework, comprising three interconnected components. First, we introduce a unified Attention-based Dynamic Multiview Spatiotemporal Graph (ADMSTG) architecture that integrates spatiotemporal and view-aware attention mechanisms, enabling the effective capture of complex cross-view relationships. Building upon this architecture, we then develop a dedicated Multiview Attention Spatiotemporal (MVAS) search space, which systematically automates the selection of optimal attention operations. Then, a specialized differentiable search algorithm efficiently explores the MVAS space to dynamically identify architecture variations specifically tailored to dynamic multiview spatiotemporal graphs. Extensive experiments on benchmark datasets show that ADMGNAS consistently outperforms SOTA methods, proving its effectiveness and adaptability.

Deploying large language models (LLMs) at the wireless edge is a promising solution to meet the low-latency, high-computation demands of next-generation AI applications. Although the existing literature has introduced approaches to enable distributed LLM inference, these methods largely overlook the distinct computational and communication characteristics of the two-phase LLM inference process—the pre-fill and decode phases. This oversight leads to suboptimal performance and limits scalability in real-world deployments. To address these issues, we propose a novel collaborative inference framework that strategically minimizes inference latency by optimally distributing computational loads across edge devices, the edge server, and the cloud. Our approach introduces a hybrid framework that combines head-wise parallel processing with layer-wise partitioning of LLM models, supported by a dual-phase optimization strategy. In the pre-fill phase, we optimize assigning attention heads to selected edge devices for parallel computation and efficient resource use. We then optimize for minimal latency by selecting participants, determining head assignments per device, and allocating bandwidth while meeting all constraints. In the de-code phase, our framework adaptively decides whether to execute computations locally on the edge server, offload them to the cloud, or redistribute tasks among edge devices, optimizing this decision based on the remaining latency budget and the sequential nature of the decode phase. The simulation results demonstrate that the proposed framework significantly outperforms the baseline methods, achieving a 56% reduction in inference latency, 40% improvement in bandwidth efficiency and 35% improvement in resource utilization.

Smart electric vehicle charging stations (EVCSs) are crucial in advancing sustainable transportation by scheduling charging based on user preferences and grid constraints. However, their reliance on digital communication makes them vulnerable to attacks that can shift the EV aggregator’s load profile to different times, leading to substantial financial losses. They can also alter charging times in ways that degrade battery health and overburden the grid. Although the existing literature has explored various strategies to mitigate these risks, most prior work has focused on simple, handcrafted charge manipulation attacks (CMAs). This makes them often fall short when confronted with artificially intelligent methods to remain undetected. To address these limitations, we propose a novel framework that both generates and defends against highly evasive CMAs. First, we utilize deep reinforcement learning (DRL) to craft advanced, stealthy attacks capable of bypassing intrusion detection systems (IDS). Second, we introduce an IDS built on LSTM variational autoencoders, which captures the nuanced temporal dependencies of smart CMAs, as well as intricate patterns. This enables our IDS to significantly enhance the detection and mitigation of complex threats. We conduct extensive simulations using real-world datasets, which reveal critical security gaps in existing benchmark approaches while highlighting the strong performance of our proposed framework. Notably, our IDS achieves detection accuracies of 0.97, 0.96, and 0.96 across different scenarios, even against highly evasive CMAs.

Clustered Federated Multi-task Learning (CFL) has emerged as a promising technique to address statistical challenges, particularly with non-independent and identically distributed (non-IID) data across users. However, existing CFL studies entirely rely on the impractical assumption that devices possess access to accurate ground-truth labels. This assumption becomes specifically problematic in hierarchical wireless networks (HWNs), with vast unlabeled data and dual-level model aggregation, not only leading to slowing down convergence speeds and extending processing times but also resulting in increased resource consumption. To this end, we propose Clustered Federated Semi-Supervised Learning (CFSL), a novel framework tailored for more realistic scenarios in HWNs. We leverage specialized models resulting from device clustering and present two prediction model schemes, the best-performing specialized model and the weighted-averaging ensemble model, to correctly label unlabeled, unseen data. For the best-performing specialized model scheme, a specialized model excelling in label prediction for a specific device is assigned to correctly label the unlabeled data, even when the data originates from other environments, while the weighted-averaging ensemble model combines all specialized models into a unified model, capturing more details from broader data distributions across edge networks. The CFSL also introduces two novel prediction time schemes, split-based and stopping-based, for accurately timing the labeling process, alongside two strategic device selection schemes, greedy and round-robin, upon reaching each cluster’s stopping point. Extensive testing validates CFSL’s superiority over existing models in labeling and testing accuracies and resource efficiency, achieving up to 51% energy savings.

Autonomous Vehicles (AVs) represent a transformative advancement in the transportation industry. These vehicles have sophisticated sensors, advanced algorithms, and powerful computing systems that allow them to navigate and operate without direct human intervention. However, AVs’ systems still get overwhelmed when they encounter a complex dynamic change in the environment resulting from an accident or a roadblock for maintenance. The advanced features of Sixth Generation (6G) technology are set to offer strong support to AVs, enabling real-time data exchange and management of complex driving maneuvers. This paper proposes a Multi-Agent Reinforcement Learning (MARL) framework to improve AVs’ decision-making in dynamic and complex Intelligent Transportation Systems (ITS) utilizing 6G-V2X communication. The primary objective is to enable AVs to avoid roadblocks efficiently by changing lanes while maintaining optimal traffic flow and maximizing the mean harmonic speed. To ensure realistic operations, key constraints such as minimum vehicle speed, roadblock count, and lane change frequency are integrated. We train and test the proposed MARL model with two traffic simulation scenarios using the SUMO and TraCI interface. Through extensive simulations, we demonstrate that the proposed model adapts to various traffic conditions and achieves efficient and robust traffic flow management. Specifically, the proposed approach results in a harmonic mean speed increase of up to 15% and a reduction in lane-change frequency by 10%. The trained model effectively navigates dynamic roadblocks, promoting improved traffic efficiency in AV operations with more than 70% efficiency over other benchmark solutions.

Semantic Communication (SemCom) systems, em-powered by deep learning (DL), represent a paradigm shift in data transmission. These systems prioritize the significance of content over sheer data volume. However, existing SemCom designs face challenges when applied to diverse computational capabilities and network conditions, particularly in time-sensitive applications. A key challenge is the assumption that diverse devices can uniformly benefit from a standard, large DL model in SemCom systems. This assumption becomes increasingly impractical, especially in high-speed, high-reliability applications such as industrial automation or critical healthcare. Therefore, this paper introduces a novel SemCom framework tailored for heterogeneous, resource constrained edge devices and computation-intensive servers. Our approach employs dynamic knowledge distillation (KD) to customize semantic models for each device, balancing computational and communication constraints while ensuring Quality of Service (QoS). We formulate an optimization problem and develop an adaptive algorithm that iteratively refines semantic knowledge in edge devices, resulting in better models tailored to their resource profiles. This algorithm strategically adjusts the granularity of distilled knowledge, enabling devices to maintain high semantic accuracy for precise inference tasks, even under unstable network conditions. Extensive simulations demonstrate that our approach significantly reduces model complexity for edge devices, leading to better semantic extraction and achieving the desired QoS.

Today, wireless networks are becoming responsible for serving intelligent applications, such as extended reality and metaverse, holographic telepresence, autonomous transportation, and collaborative robots. Although current fifth-generation (5G) networks can provide high data rates in terms of Giga-bytes/second, they cannot cope with the high demands of the aforementioned applications, especially in terms of the size of the high-quality live videos and images that need to be communicated in real-time. Therefore, with the help of artificial intelligence (AI)-based future sixth-generation (6G) networks, the semantic communication concept can provide the services demanded by these applications. Unlike Shannon's classical information theory, semantic communication urges the use of the semantics (meaningful contents) of the data in designing more efficient data communication schemes. Hence, in this paper, we model semantic communication as an energy minimization framework in heterogeneous wireless networks with respect to delay and quality-of-service constraints. Then, we propose a sub-optimal solution to the NP-hard combinatorial mixed-integer nonlinear programming problem (MINLP) by utilizing efficient techniques such as discrete optimization variables' relaxation. In addition, AI-based autoencoder and classifier are trained and deployed to perform semantic extraction, reconstruction, and classification services. Finally, we compare our proposed sub-optimal solution with different state-of-the-art methods, and the obtained results demonstrate its superiority.

The increasing popularity of electric vehicles (EVs) necessitates robust defenses against sophisticated cyber threats. A significant challenge arises when EVs intentionally provide false information to gain higher charging priority, potentially causing grid instability. While various approaches have been proposed in existing literature to address this issue, they often overlook the possibility of attackers using advanced techniques like deep reinforcement learning (DRL) or other complex deep learning methods to achieve such attacks. In response to this, this paper introduces a hierarchical adversarial framework using DRL (HADRL), which effectively detects stealthy cyberattacks on EV charging stations, especially those leading to denial of charging. Our approach includes a dual approach, where the first scheme leverages DRL to develop advanced and stealthy attack methods that can bypass basic intrusion detection systems (IDS). Second, we implement a DRL-based scheme within the IDS at EV charging stations, aiming to detect and counter these sophisticated attacks. This scheme is trained with datasets created from the first scheme, resulting in a robust and efficient IDS. We evaluated the effectiveness of our framework against the recent literature approaches, and the results show that our IDS can accurately detect deceptive EVs with a low false alarm rate, even when confronted with attacks not represented in the training dataset.

Clustered Federated Multi-task Learning (CFL) has gained considerable attention as an effective strategy for over-coming statistical challenges, particularly when dealing with non-independent and identically distributed (non-IID) data across multiple users. However, much of the existing research on CFL operates under the unrealistic premise that devices have access to accurate ground-truth labels. This assumption becomes especially problematic in, especially hierarchical wireless networks (HWNs), where edge networks contain a large amount of unlabeled data, resulting in slower convergence rates and increased processing times-particularly when dealing with two layers of model aggregation. To address these issues, we introduce a novel frame-work-Clustered Federated Semi-Supervised Learning (CFSL), designed for more realistic HWN scenarios. Our approach leverages a best-performing specialized model algorithm, wherein each device is assigned a specialized model that is highly adept at generating accurate pseudo-labels for unlabeled data, even when the data stems from diverse environments. We validate the efficacy of CFSL through extensive experiments, comparing it with existing methods highlighted in recent literature. Our numerical results demonstrate that CFSL significantly improves upon key metrics such as testing accuracy, labeling accuracy, and labeling latency under varying proportions of labeled and unlabeled data while also accommodating the non-IID nature of the data and the unique characteristics of wireless edge networks.

As smart grids (SG) increasingly rely on advanced technologies like sensors and communication systems for efficient energy generation, distribution, and consumption, they become enticing targets for sophisticated cyber-attacks. These evolving threats demand robust security measures to maintain the stability and resilience of modern energy systems. While extensive research has been conducted, a comprehensive exploration of proactive cyber defense strategies utilizing Deep Learning (DL) in SG remains scarce in the literature. This survey bridges this gap, studying the latest DL techniques for proactive cyber defense. The survey begins with an overview of related works and our distinct contributions, followed by an examination of SG infrastructure. Next, we classify various cyber defense techniques into reactive and proactive categories. A significant focus is placed on DL-enabled proactive defenses, where we provide a comprehensive taxonomy of DL approaches, highlighting their roles and relevance in the proactive security of SG. Subsequently, we analyze the most significant DL-based methods currently in use. Further, we explore Moving Target Defense, a proactive defense strategy, and its interactions with DL methodologies. We then provide an overview of benchmark datasets used in this domain to substantiate the discourse. This is followed by a critical discussion on their practical implications and broader impact on cybersecurity in Smart Grids. The survey finally lists the challenges associated with deploying DL-based security systems within SG, followed by an outlook on future developments in this key field.

Honeypot technologies provide an effective defense strategy for the Industrial Internet of Things (IIoT), particularly in enhancing the Advanced Metering Infrastructure’s (AMI) security by bolstering the network intrusion detection system. For this security paradigm to be fully realized, it necessitates the active participation of small-scale power suppliers (SPSs) in implementing honeypots and engaging in collaborative data sharing with traditional power retailers (TPRs). To motivate this interaction, TPRs incentivize data sharing with tangible rewards. However, without access to an SPS’s confidential data, it is daunting for TPRs to validate shared data, thereby risking SPSs’ privacy and increasing sharing costs due to voluminous honeypot logs. These challenges can be resolved by utilizing Federated Learning (FL), a distributed machine learning (ML) technique that allows for model training without data relocation. However, the conventional FL algorithm lacks the requisite functionality for both the security defense model and the rewards system of the AMI network. This work presents two solutions: first, an enhanced and cost-efficient FedAvg algorithm incorporating a novel data quality measure, and second, FedPot, the development of an effective security model with a fair incentives mechanism under an FL architecture. Accordingly, SPSs are limited to sharing the ML model they learn after efficiently measuring their local data quality, whereas TPRs can verify the participants’ uploaded models and fairly compensate each participant for their contributions through rewards. Moreover, the proposed scheme addresses the problem of harmful participants who share subpar models while claiming high-quality data through a two-step verification approach. Simulation results, drawn from realistic mircorgrid network log datasets, demonstrate that the proposed solutions outperform state-of-the-art techniques by enhancing the security model and guaranteeing fair reward distributions.

Adopting honeypot defenses is a promising technology for protecting the industrial Internet of Things (IIoT), particularly the Advanced Metering Infrastructure (AMI). The effectiveness of AMI defense is entirely reliant on the deployment of honeypots by small-scale power suppliers (SPSs) and then sharing the defense data with traditional power retailers (TPRs) to build anomaly detectors. TPR encourages the SPSs to share their collected honeypot logs by designing proper rewards. However, TPRs cannot confirm the validity of the shared defense data unless they have access to SPSs' private data, compromising their privacy since SPSs may be reluctant to disclose their private collected data. In addition, the honeypot logs are large, which increases the sharing costs. Federated Learning (FL), as a promising privacy-preserving machine learning technique, can solve these problems. Yet, the conventional FL algorithm cannot optimally fit the security defense model and the associated returned rewards in the AMI network. Thus, using two proposed solutions, including a modified FedAvg algorithm, this paper proposes a privacy-preserving and cost-effective FL framework for efficient security model development and fair rewards, in which SPSs can share only the learned ML model while TPR can validate the quality of the uploaded models and compensate all participants with appropriate rewards that reflect their contributions. The proposed framework also considers malicious participants who claim high-quality data while sharing bad models. We run extensive simulations on realistic log datasets, and the results show that the proposed solutions outperform existing approaches.

The ever-expanding landscape of advanced applications and services, as well as the associated emerging attacks in the zero-touch network and service management (ZSM) paradigm, necessitates novel approaches to manage complex network infrastructures while addressing the security requirements of beyond 5G networks. To address this issue, we present a cutting-edge, novel semi-supervised federated learning approach that incorporates a Deep Reinforcement Learning (DRL) agent for real-time defense system updates. Specifically, we propose the DRL-FedUSS framework, which stands for DRL-based Federated Uncertainty-guided Semi-Supervised learning. DRL-FedUSS is designed explicitly for Label-at-Client scenarios to accelerate the training convergence when clients hold a scarcity of labeled and an abundance of unlabeled network traffic samples. The DRL-FedUSS framework integrates a DRL agent that intelligently selects the most informative samples with a real-time adaptive threshold for data annotation, considering uncertainty, time, budget constraints, and, most importantly, the convergence rate and confidence level constraints. Our extensive simulations on realistic non-independent and identically distributed (non-IID) datasets prove that the DRL-FedUSS framework outperforms baseline approaches, achieving superior intrusion detection accuracy, reducing the associated cost, and accelerating the convergence rate with minimal network traffic labeled data.

Clustered federated multi task learning (CFL) is introduced as an effective and efficient approach for addressing statistical challenges such as non-independent and identically distributed (non-IID) data among workers. Workers in CFL are clustered in groups based on similarity (i.e., cosine similarity) in their data distributions, in which each cluster is equipped with an efficient specialized model. However, this approach can be costly and time-consuming when implemented in hierarchical wireless networks (HWNs) due to uploading several models at every round to enable the cloud server to capture the incongruent data distribution from different edge networks. This brings about the need for novel solutions to address these challenges. To this end, this paper introduces a framework with two cloud-based model aggregation approaches, round-based and split-based, so as to minimize latency and resource consumption while attaining satisfying personalized accuracy. In the round-based scheme, the cloud aggregates the models from the edge servers after a predetermined number of rounds. As for the split-based scheme, the models are collected by the cloud only when edge servers perform the split. Extensive experiments are conducted to evaluate and compare the proposed heuristics against approaches presented in the recent literature. The numerical results and findings demonstrate that the proposed heuristics significantly conserve resources by reducing energy consumption by 60% and saving time, all while accelerating the convergence rate for cluster workers across various edge networks.

The majority of streaming Internet of Things (IoT) applications use machine learning models to identify and classify streaming inputs before forwarding them for further processing. These streaming IoT systems, however, are vulnerable to poisoning and adversarial attacks. An adversary deliberately modifies the input by adding a small perturbation during the communication to fool the class label into producing an arbitrary or specific output. The increasing number of well-developed, imperceptible attacks necessitates more sophisticated countermeasures. To this end, this paper underlines this problem and proposes a new scheme based on committee-based machine learning models: some have experience with only benign inputs, and others with benign and adversarial inputs. Then, the probabilities of the outputs of these pairs' models are utilized. The KL-divergence after that is applied to identify, detect, and mitigate such streaming attacks. Specifically, we use the uncertainty measures between the output of mitigation and non-mitigation ML models as a proxy to identify adversely attacked inputs. We use traffic sign classification in autonomous vehicle technology as a streaming IoT application. Our experiments demonstrate that the proposed approach can detect and mitigate adversarial attacks with high confidence for the white-box attack.

Datasets are essential for training machine learning algorithms and ensuring accurate classifications. However, obtaining such datasets, especially those relating to IEC61850 GOOSE messages in smart grids, poses a significant challenge for researchers. Privacy regulations and potential misuse of industrial data have compounded this problem, necessitating alternative methods for generating datasets. In this paper, we detail the design and implementation of a simulation testbed that uses MATLAB/Simulink, OpenPLC and the lib61850 library. This testbed simulates a smart grid system and generates IEC61850 GOOSE messages for dataset creation. We assess the testbed performance using a simplified smart grid model with multiple protection relays, also known as Intelligent Electronic Devices (IEDs), enabling us to measure the response time of the protection system under various fault conditions. The testbed is flexible, allowing for design alterations and expansions, which aids researchers in generating diverse datasets to represent various smart grid networks. This flexibility will increase the availability of valuable datasets and enable the broader application of machine-learning techniques in this domain.

Advanced Information Communication Technology (ICT) is used in smart grid systems to introduce intelligence and efficiency, potentially outperforming conventional power systems. A fundamental component of a smart grid system is the Smart Meters (SMs), which are integrated with billing utilities, such as national control centers (NCC), and advanced metering infrastructure (AMI). However, like most emerging technologies, some security vulnerabilities and attacks were found. In this paper, we address such vulnerabilities, specifically associated with SMs, that occur when energy consumption is reported to the billing system, specifically through the IEC-60870-5-104(IEC-104) protocol. Since existing datasets do not include sufficient data related to such vulnerabilities, especially in SM with IEC-104 protocol communication, we developed a testbed with a virtual environment and generated a dataset with and without attack vectors. We then proposed a novel anomaly detection algorithm based on LSTM autoencoder, which combines the functional benefits of LSTM and the deep learning of autoencoders. The model's performance is evaluated against two popular attacks, MITM and Replay, and our result shows that the replay attack is harder to find since the attack is executed without data alteration.

In the 5G/B5G network paradigms, intelligent medical devices known as the Internet of Medical Things (IoMT) have been used in the healthcare industry to monitor remote users’ health status, such as elderly monitoring, injuries, stress, and patients with chronic diseases. Since IoMT devices have limited resources, mobile edge computing (MEC) has been deployed in 5G networks to enable them to offload their tasks to the nearest computational servers for processing. However, when IoMTs are far from network coverage or the computational servers at the terrestrial MEC are overloaded/emergencies occur, these devices cannot access computing services, potentially risking the lives of patients. In this context, unmanned aerial vehicles (UAVs) are considered a prominent aerial connectivity solution for healthcare systems. In this article, we propose a multiagent federated reinforcement learning (MAFRL)-based resource allocation framework for a multi-UAV-enabled healthcare system. We formulate the computation offloading and resource allocation problems as a Markov decision process game in federated learning with multiple participants. Then, we propose an MAFRL algorithm to solve the formulated problem, minimize latency and energy consumption, and ensure the quality of service. Finally, extensive simulation results on a real-world heartbeat data set prove that the proposed MAFRL algorithm significantly minimizes the cost, preserves privacy, and improves accuracy compared to the baseline learning algorithms.

Clustered federated Multitask learning is introduced as an efficient technique when data is unbalanced and distributed amongst clients in a non-independent and identically distributed manner. While a similarity metric can provide client groups with specialized models according to their data distribution, this process can be time-consuming because the server needs to capture all data distribution first from all clients to perform the correct clustering. Due to resource and time constraints at the network edge, only a fraction of devices is selected every round, necessitating the need for an efficient scheduling technique to address these issues. Thus, this paper introduces a two-phased client selection and scheduling approach to improve the convergence speed while capturing all data distributions. This approach ensures correct clustering and fairness between clients by leveraging bandwidth reuse for participants spent a longer time training their models and exploiting the heterogeneity in the devices to schedule the participants according to their delay. The server then performs the clustering depending on predetermined thresholds and stopping criteria. When a specified cluster approximates a stopping point, the server employs a greedy selection for that cluster by picking the devices with lower delay and better resources. The convergence analysis is provided, showing the relationship between the proposed scheduling approach and the convergence rate of the specialized models to obtain convergence bounds under non-i.i.d. data distribution. We carry out extensive simulations, and the results demonstrate that the proposed algorithms reduce training time and improve the convergence speed by up to 50% while equipping every user with a customized model tailored to its data distribution.

Federated edge learning (FEEL) is a rapidly growing distributed learning technique for next-generation wireless edge systems. Smart systems across various application domains face challenges, such as data heterogeneity, limited wireless resources, and device heterogeneity, which necessitate intelligent participant selection schemes that accelerate convergence rates. Consequently, this article presents joint participant selection and bandwidth allocation schemes to address these challenges. First, we formulate an optimization problem that considers communication and computation latencies, as well as imbalanced data distribution, while meeting round deadlines and bandwidth constraints. To address the combinatorial problems of participant selection, we employ a relaxation method followed by a proposed priority selection algorithm to select near-optimal participants. The proposed algorithm initially prioritizes participants with larger datasets, effective channel states, and better CPU speeds. To address data heterogeneity, we propose a randomized deadline-controlling algorithm that diversifies updates by allowing the edge server to include different participants with fewer data samples in training rounds. The proposed algorithms offer near-optimal performance compared to the brute-force method. Experiments demonstrate that our proposed scheme accelerates the convergence rate by up to 55% under extensive non-IID settings compared to benchmarks. Furthermore, the deadline-controlling algorithm improves performance at high levels of data heterogeneity, resulting in faster FEEL systems.

In 6G networks, unmanned aerial vehicles (UAVs) can serve as aerial flying base stations (AFBS) with aerial mobile edge computing (AMEC) server capabilities. AFBS is an increasingly popular solution for delivering time-sensitive applications, extending network coverage, and assisting ground base stations in the healthcare systems for remote areas with limited infrastructure. Furthermore, the UAVs are deployed in the healthcare system to support the Internet of medical things (IoMT) devices in data collection, medical equipment distribution, and providing smart services. However, ensuring the privacy and security of patients' data with the limited UAV resources is a major challenge. In this paper, we present a federated deep reinforcement learning framework for resource allocation in UAV-enabled healthcare systems, where IoMT devices send their trained model parameters without transmitting sensitive raw data to the AMEC server. In the proposed framework, the IoMT device is associated with AFBS based on the quality of the data and its demand in order to maximize learning efficiency and accuracy. This work aims to minimize the computation costs of the IoMT devices while considering UAV resources and the fairness of UAV coverage. Simulation results prove that our proposed algorithm outperforms other baseline algorithms in learning accuracy and computational cost.

In recent years, Federated Edge Learning has gained interest from both industry and academia for deployment at the wireless network edge. However, some resource-restricted edge devices (EDs) bear more computation and communication loads due to the heterogeneity of data and resources. Several approaches have been proposed in the literature to reduce energy costs by scheduling only a few EDs to complete training tasks based on their energy budgets. Nevertheless, from a practical perspective, the incongruent data distribution cannot be captured, resulting in a biased model for EDs that are frequently selected. Furthermore, the frequently scheduled devices deplete their energy quickly, making them inaccessible. Thus, this paper proposes a novel scheduling policy based on the historical participation of each ED that ensures an unbiased model while balancing learning tasks so that all EDs consume equivalent energy at the end of the training. We formulate an optimization problem based on Jain's fairness index, followed by tractable algorithms to solve this problem. Extensive experiments have been conducted, and the results show that the proposed algorithm balances the energy consumption among EDs and accelerates the convergence rate while achieving satisfactory performance.

Federated Learning (FL) is one of the hot research topics, and it utilizes Machine Learning (ML) in a distributed manner without directly accessing private data on clients. How-ever, FL faces many challenges, including the difficulty to obtain high accuracy, high communication cost between clients and the server, and security attacks related to adversarial ML. To tackle these three challenges, we propose an FL algorithm inspired by evolutionary techniques. The proposed algorithm groups clients randomly in many clusters, each with a model selected randomly to explore the performance of different models. The clusters are then trained in a repetitive process where the worst performing cluster is removed in each iteration until one cluster remains. In each iteration, some clients are expelled from clusters either due to using poisoned data or low performance. The surviving clients are exploited in the next iteration. The remaining cluster with surviving clients is then used for training the best FL model (i.e., remaining FL model). Communication cost is reduced since fewer clients are used in the final training of the FL model. To evaluate the performance of the proposed algorithm, we conduct a number of experiments using FEMNIST dataset and compare the result against the random FL algorithm. The experimental results show that the proposed algorithm outperforms the baseline algorithm in terms of accuracy, communication cost, and security.

Federated learning (FL) is a promising paradigm for future sixth-generation wireless systems to underpin network edge intelligence for smart cities applications. However, most of the data collected by the Internet of Things devices in such applications is unlabeled, necessitating the use of semi-supervised learning. Existing studies have introduced solutions to run semi-supervised FL; however, they overlooked the inherent critical impacts of the wireless characteristics at the network edge. We fill this gap by proposing novel solutions to run semi-supervised FL over wireless network edge, considering the limited computation and communication resources and deadline constraints and realizing that unlabeled data can be automatically labeled during the training rounds to improve the performance of the global model. The problem is first formulated as an optimization problem followed by a two-phase solution. In the first phase, we propose a bisection-based algorithm to find the transmit power and local processing speed that optimally fit the new injected labeled data. In the second phase, we propose three algorithms to control the local updates and injected samples that meet the deadline constraint. We analyze the performance of each algorithm concerning the tradeoffs between learning performance, training time, and total energy consumption. Targeting two applications in smart cities, human activity recognition and object detection, we conduct extensive simulations using realistic federated data sets under nonindependent and identically distributed settings. Numerical results show that the proposed algorithms effectively utilize unlabeled samples while accounting for the characteristics of wireless edge networks in smart cities.

Clustered Federated Multitask Learning (CFL) was introduced as an efficient scheme to obtain reliable specialized models when data is imbalanced and distributed in a non-i.i.d. (non-independent and identically distributed) fashion amongst clients. While a similarity measure metric, like the cosine similarity, can be used to endow groups of the client with a specialized model, this process can be arduous as the server should involve all clients in each of the federated learning rounds. Therefore, it is imperative that a subset of clients is selected periodically due to the limited bandwidth and latency constraints at the network edge. To this end, this paper proposes a new client selection algorithm that aims to accelerate the convergence rate for obtaining specialized machine learning models that achieve high test accuracies for all client groups. Specifically, we introduce a client selection approach that leverages the devices' heterogeneity to schedule the clients based on their round latency and exploits the bandwidth reuse for clients that consume more time to update the model. Then, the server performs model averaging and clusters the clients based on predefined thresholds. When a specific cluster reaches a stationary point, the proposed algorithm uses a greedy scheduling algorithm for that group by selecting the clients with less latency to update the model. Extensive experiments show that the proposed approach lowers the training time and accelerates the convergence rate by up to 50% while imbuing each client with a specialized model that is fit for its local data distribution.

Recognizing the patient's emotions using deep learning techniques has attracted significant attention recently due to technological advancements. Automatically identifying the emotions can help build smart healthcare centers that can detect depression and stress among the patients in order to start the medication early. Using advanced technology to identify emotions is one of the most exciting topics as it defines the relationships between humans and machines. Machines learned how to predict emotions by adopting various methods. In this survey, we present recent research in the field of using neural networks to recognize emotions. We focus on studying emotions' recognition from speech, facial expressions, and audio-visual input and show the different techniques of deploying these algorithms in the real world. These three emotion recognition techniques can be used as a surveillance system in healthcare centers to monitor patients. We conclude the survey with a presentation of the challenges and the related future work to provide an insight into the applications of using emotion recognition.

Privacy concerns are considered one of the main challenges in smart cities as sharing sensitive data induces threatening problems in people's lives. Federated learning has emerged as an effective technique to avoid privacy infringement as well as increase the utilization of the data. However, there is a scarcity in the amount of labeled data and an abundance of unlabeled data collected in smart cities; hence there is a necessity to utilize semi-supervised learning. In this paper, we present the primary design aspects for enabling federated learning at the edge networks taking into account the problem of unlabeled data. We propose a semi-supervised federated edge learning method called FedSem that exploits unlabeled data in real-time. FedSem algorithm is divided into two phases. The first phase trains a global model using only the labeled data. In the second phase, Fedsem injects unlabeled data into the learning process using the pseudo labeling technique and the model developed in the first phase to improve the learning performance. We carried out several experiments using the traffic signs dataset as a case study. Our results show that FedSem can achieve accuracy by up to 8% by utilizing the unlabeled data in the learning process.

Received Signal Strength (RSS) fingerprint-based localization has attracted a lot of research effort and cultivated many commercial applications of location-based services due to its low cost and ease of implementation. Many studies are exploring the use of deep learning (DL) algorithms for localization. DL's ability to extract features and to classify autonomously makes it an attractive solution for fingerprint-based localization. These solutions require frequent retraining of DL models with vast amounts of measurements. Although crowdsourcing is an excellent way to gather immense amounts of data, it jeopardizes the privacy of participants, as it requires to collect labeled data at a centralized server. Recently, federated learning has emerged as a practical concept in solving the privacy preservation issue of crowdsourcing participants by performing model training at the edge devices in a decentralized manner; the participants do not expose their data anymore to a centralized server. This paper presents a novel method utilizing federated learning to improve the accuracy of RSS fingerprint-based localization while preserving the privacy of the crowdsourcing participants. Employing federated learning allows ensuring preserving the privacy of user data while enabling an adequate localization performance with experimental data captured in real-world settings. The proposed method improved localization accuracy by 1.8 meters when used as a booster for centralized learning and achieved satisfactory localization accuracy when used standalone.

Wireless sensor network has proven to be a good candidate for many monitoring applications such as habitat monitoring, structural health monitoring, pipeline monitoring, etc. Pipeline monitoring is a challenging application where the sensors are placed in a linear topology. This linear topology requires careful attention in placing sensors to ensure robustness against anomaly, minimize the energy consumption and maximize the network lifetime. This paper investigates this problem by improving and evaluating the performance of two greedy node placement approaches. In contrast to existing work, we have validated experimentally the 31 power levels of CC2420 TelosB chipon and their corresponding transmission ranges. Having more power-level resolution yields less energy consumption and longer lifetime compared to traditional 8 power levels. Extensive simulation and real experiments have been conducted. The results demonstrate 23% extension in the lifetime when all power levels are adopted.