Physical layer characteristics of a wireless channel, which can be measured independently by the two communicating parties and yield near-identical results due to the channel reciprocity property, have been shown to be an important source of shared secrecy generation. Various types of channel state information (CSI), such as the received signal strength (RSS) and the channel impulse response (CIR) can be utilized for this purpose. Through periodic probing of the CSI, a continuous cycle of secret bit generation and key renewal can be maintained. However, many forms of wireless CSI inherently have substantial temporal correlation, which may hinder the secrecy generation process. Accordingly, various autocorrelation reduction (decorrelation) methods have been proposed, using either sub-sampling approaches that discard potentially valuable CSI data, or, computationally expensive transform domain approaches such as the Discrete Cosine Transform (DCT), Karhunen-Loeve Transform (KLT), and principal component analysis (PCA) that may not be feasible or desirable for resource and energy constrained devices. This paper proposes a low-complexity method for reducing the autocorrelation of the CSI measurements through a reordering of the data based on integer sequences such as the Fibonacci sequences, and applies it to various types of CSI data that represent both the individual path level CIR and the aggregate level multipath gain or RSS. We evaluate the performance of the method in three standard multipath ITU channel models. Fibonacci sequences are observed to be an effective means of decorrelating the channel measurement data, thereby eliminating the need for computationally intensive methods.

AI-powered face recognition has become essential to various IoT applications, including home automation, security systems, and personalized services. While these systems offer significant advancements, they still face critical challenges related to accuracy and privacy. One major issue is class imbalance, which is common in face recognition systems where certain demographic groups are underrepresented. This imbalance results in biased models, compromising the accuracy and fairness of these systems. Furthermore, traditional centralized training methods can expose sensitive facial data, raising serious privacy concerns. Federated Learning (FL) has emerged as a solution to improve model training by enabling collaboration across devices without sharing sensitive data. However, it also worsens the issue of data heterogeneity. This paper proposes a Hierarchical Federated Learning (HFL) framework to address class imbalance while preserving privacy. By aggregating local models at different hierarchical levels, the framework mitigates data imbalance and enhances fairness in face recognition systems. Additionally, a privacy-preserving mechanism based on Secure Multi-Party Computation (SMPC) is implemented to ensure data security during the training process.

This research proposed an end-to-end object detection network based on Kolmogorov-Arnold Networks (KANs)-Detection Transformer (DETR). KANs block was introduced into encoder-decoder structure instead of the full connection layer to dynamically learn the activation function and improve the robustness and accuracy of the model. Experiments showed that the detection capability of KANs-DETR on multicategory object detection was better than that of HGNetv2 and Swin Transformer as backbone. Furthermore, in order to solve the problem of insensitivity to small objects, the Squeeze-and-Excitation module was applied for feature fusion and presented better performance. The KANs-DETR achieved high detection accuracy and efficiency in handling small objects in complex scenes, providing a new perspective for network optimization.

There are the excessive queries to the targeted model during the generates of gray-box adversarial examples for speaker recognition systems, which result in high costs of attacks. In this paper, a fast generates algorithm of gray-box adversarial example is proposed based on FakeBob, named F-FakeBob. This algorithm introduces a threshold mechanism for optimization to the optimization strategy of gradient. Only when the increasing of the confidence scores of the adversarial example before and after optimizing is less than the threshold, the gradient is recalculated for the next iteration. By reducing the frequency of gradient calculations, the number of queries to the targeted system is decreased. Experiments on three public datasets of speech, TIMIT, Common Voice, and Voxceleb2, are conducted to generate adversarial examples. The targeted speaker recognition models are based on ECAPA-TDNN and TitaNet architectures. The experimental results show that F-FakeBob can achieve a targeted attack success rate of 99.2% and the number of queries are effectively reduced in the adversarial example generates, with an average query reduction of 25.71% compared to FakeBob.

Ransomware has emerged as one of the most prevalent and destructive cyber attacks confronting global organizations. By locking critical devices or encrypting essential data and then demanding payment for restoration, ransomware attacks disrupt operations, result in significant financial losses, and damage organizational reputations. In particular, zero-day ransomware attacks, which attempt to exploit previously unknown vulnerabilities, pose a severe threat to existing cyber security solutions. Due to the lack of training data, detection of zero-day ransomware attacks remains a significant challenge. This paper proposes a novel zero-day ransomware detection framework that integrates a refined Conditional Variational Autoencoder (CVAE) with a 1D Convolutional Neural Network (1D-CNN). The encoder of the CVAE model comprises a posterior network and a parallel prior network. Using variational coding, the posterior network maps behavioral features of software samples from known families into a latent space, represented by a fixed multivariate Gaussian distribution with a diagonal covariance matrix. Simultaneously, the prior network eliminates dependency on class labels while maintaining distributional consistency with the posterior network via Kullback-Leibler (KL) divergence minimization. This dual-network structure enables unified latent space mapping for both labeled and unlabeled samples, effectively narrowing distributional discrepancies between software samples from known and unknown families. The harmonized latent representations subsequently enhance the discriminative capability of the 1D-CNN classifier in detecting zero-day ransomware. The comprehensive experimental results have verified that the proposed method can effectively detect zero-day ransomware attacks.

Modern distributed storage systems increasingly employ Locally Repairable Codes (LRCs) to provide reliable, low-cost data storage with high repair efficiency. However, the presence of stragglers, i.e., nodes that unpredictably slow down, can significantly impact access latency. Traditional approaches for handling stragglers, such as detection, blacklisting, or speculative execution, are often insufficient for efficient straggler tolerance. In this paper, we show how an in-memory caching strategy coupled with LRCs can bypass stragglers without relying on precise straggler detection. We propose LocalityCache, a novel in-memory caching mechanism designed for LRC-coded distributed storage systems, which effectively mitigates the impact of stragglers by caching local parity blocks. We provide theoretical guarantees for LocalityCache and show that caching local parity blocks minimizes the likelihood of encountering stragglers. Additionally, we devise optimized workflows for write, read, and repair operations under LocalityCache to ensure system efficiency. We implement LocalityCache in a distributed key-value store prototype atop Redis. Our extensive testbed evaluations show that LocalityCache can significantly reduce read latency of the baselines by up to 73.6% in the presence of stragglers.

The growing reliance on big data frameworks such as Hadoop has revolutionized data processing across various domains, enabling large-scale storage and distributed computation. Hadoop is widely employed in real-world applications such as high-performance computation tasks, e-commerce and data analysis in healthcare. However, the efficiency of Hadoop systems is often hampered by faults and anomalies, with stragglers emerging as one of the most prevalent issues. Stragglers disrupt workflows, waste resources and degrade system performance. While existing anomaly detection models employ methods like median analysis or static thresholds, they often struggle with issues such as high false positives, lack of adaptability and poor handling of complex heterogeneous environments. To address these challenges, this paper presents Plabs, a flexible stragglers detection framework for Hadoop. The framework comprises two core components: (1) a Monitoring Module providing real-time tracking of cluster resources and task progress and (2) a Pluggable AI-based straggler detection module, designed for precise straggler task identification. By leveraging advanced monitoring and AI-driven analysis, Plabs offers an automated, flexible and scalable solution for detecting stragglers at run-time in Hadoop clusters. We evaluated Plabs exhaustively with three Machine Learning (ML), two Deep Learning (DL) and two Large Language Models (LLMs) on five different applications in a real testbed environment. Our experiment evaluation shows that DL models outperform others in identifying Hadoop stragglers, achieving superior accuracy and reliability for all the applications.

Federated learning faces challenges with non-IID data distributions, often resulting in suboptimal performance for individual clients with the global model. To address this issue, we propose a clustered hierarchical personalized federated learning (CHPFL) framework, which provides edge-level personalization to effectively overcomes non-IID data and alleviates the overfitting in the personalization process. The three-layer framework makes the learning and personalization process more feasible compared to traditional two-layer federated learning, as edge servers typically offer greater computing power and more efficient communication with the cloud server. Specifically, we use the K-Means++ clustering algorithm to group local clients based on their model updates, ensuring that clients with similar data distributions are clustered together and assigned to the same edge server. Each edge server then generates a personalized model by blending the global model with the edge model, which is adaptively updated and optimized through multiple iterations. Additionally, we introduce a novel aggregation rule on the cloud server to produce a global model with improved performance. Experiments on the MNIST, FMNIST, and KMNIST datasets demonstrate that CHPFL effectively overcomes non-IID data distribution and outperforms HPFL, APFL, and FedALA in non-IID settings.

As modern embedded systems are increasingly network connected, their protocol stacks expose themselves as a surface that is frequently attacked. While C-based implementations such as LwIP are efficient, their lack of memory safety induces critical vulnerabilities such as buffer overflows, dangling pointers, and use-after-free, leading to remote code execution or privilege escalation. In this paper, we present LwRustIP, a memory-safe embedded networking stack reimplemented in Rust and compatible with LwIP. We also share our development experience. LwRustIP replaces unsafe linked-list memory management with a custom allocator that honors the Rust ownership semantics, leverages zero-copy techniques for inter-layer packet handoffs, and applies lock-free object pools for concurrent buffer management. These design choices ensure memory safety while maintaining performance comparable to traditional C-based implementations. We deploy LwRustIP on ARM-based embedded platforms and evaluate its correctness, performance, and memory safety. Experimental results show that LwRustIP achieves memory safety without incurring measurable performance overhead compared to the original C-based implementation. Our experience highlights the practical challenges and benefits of using Rust for low-level system components and offers guidance for future efforts in memory-safe reengineering of legacy C codebases.

The Internet of Things (IoT) and cyber-physical systems (CPS) are driving digital transformation and automation. An essential component of CPS is digital twin (DT) technology, which enables real-time synchronization between physical assets and their virtual counterparts. Battery management systems (BMS) in electric vehicles (EVs) face challenges in handling large volumes of sensor data, often leading to reduced accuracy in battery-state estimation. To address these challenges, DTs have been explored to aid real-time diagnosis and monitoring. One critical step toward the success of DTs is to have practical reference architectures. This paper presents proposes a novel six-layer DT architecture tailored for BMS, extending existing CPS/DT-BMS models by integrating high-fidelity electrochemical modeling, robust nonlinear state estimation, and interactive 3D visualization in a Metaverse environment. The architecture is designed with scalability in mind, supporting deployment on lightweight embedded platforms or via cloud-hosted rendering for resource-limited devices. We validate the approach using MATLAB to develop a thermally coupled SPMe-based DT of a lithium-ion NMC battery, synchronized with a virtual battery model in Unreal Engine for immersive visualization. Experimental results demonstrate accurate state-of-charge estimation (RMSE 0.23%) and low-latency real-time monitoring, highlighting the framework’s potential for deployment in large-scale EV BMS applications.

Due to perceptions of efficiency and significant productivity gains, various organisations, including in education, are adopting Large Language Models (LLMs) into their workflows. Educator-facing, learner-facing, and institution-facing LLMs, collectively, Educational Large Language Models (eLLMs), complement and enhance the effectiveness of teaching, learning, and academic operations. However, their integration into an educational setting raises significant cybersecurity concerns. A comprehensive landscape of contemporary attacks on LLMs and their impact on the educational environment is missing. This study presents a generalised taxonomy of fifty attacks on LLMs, which are categorised as attacks targeting either models or their infrastructure. The severity of these attacks is evaluated in the educational sector using the DREAD risk assessment framework. Our risk assessment indicates that token smuggling, adversarial prompts, direct injection, and multi-step jailbreak are critical attacks on eLLMs. The proposed taxonomy, its application in the educational environment, and our risk assessment will help academic and industrial practitioners to build resilient solutions that protect learners and institutions.

This survey examines the current state of the Metaverse, encompassing its fundamental concepts, technological framework, practical applications, and user experience to evaluate its stage of development. This paper reviews the core concepts of the Metaverse and Extended Reality (XR) and evaluates the latest advancements in hardware and software technologies. Furthermore, it examines the Metaverse’s typical applications in four key domains: education, training, medicine, and mixed life, while summarizing user feedback to identify its advantages and challenges. The feedback indicates that the Metaverse offers notable benefits, including immersive experiences, enhanced training effectiveness, cost efficiency, and improved safety. However, significant challenges remain, such as hardware performance limitations, software inefficiencies, user discomfort, health risks, and social and ethical concerns. Our analysis suggests that while the Metaverse has yet to reach full maturity, it holds great potential for future development. To further advance the field, this paper highlights key research priorities in artificial intelligence(AI), quantum computing, and social governance, providing insights for future studies.