Split inference (SI) enables users to access deep learning (DL) services without directly transmitting raw data. However, recent studies reveal that data reconstruction attacks (DRAs) can recover the original inputs from the smashed data sent from the client to the server, leading to significant privacy leakage. While various defenses have been proposed, they often result in substantial utility degradation, particularly when the client-side model is shallow. We identify a key cause of this trade-off: existing defenses apply excessive perturbation to redundant information in the smashed data. To address this issue in computer vision tasks, we propose InfoDecom, a defense framework that first decomposes and removes redundant information and then injects noise calibrated to provide theoretically guaranteed privacy. Experiments demonstrate that InfoDecom achieves a superior utility-privacy trade-off compared to existing baselines.

Hidden degenerations in industrial time series often precede observable failures, they remain undetected by standard monitoring systems until anomalies become apparent. This gap between microscopic degradation and macroscopic observation renders conventional predictors inherently reactive, as they rely on correlations in sensor data rather than uncovering the underlying, physics‑consistent degradation states. Crucially, the microscopic mechanisms governing system evolution depend on macroscopic state variables—whose measurements are expectations over microscopic probability distributions—so purely data‑driven “top‑down” or purely physics‑guided “bottom‑up” approaches cannot forecast degeneration‑entangled industrial faults. To address these challenges, we propose a Physics-Guided Bidirectional Inference Framework that represents hidden microscopic states from macroscopic measurements. Our approach uniquely combines: (1) bottom-up physics-based simulation using Continuum Damage Mechanics to model micro-scale damage evolution under environmental stressors, and (2) top-down probabilistic inference via maximum entropy formalism to estimate latent microstate distributions from sparse sensor data. This bidirectional mechanism enables early failure prediction by bridging observable measurements with unobservable degeneration. Validation on real-world railway infrastruc datasets demonstrates significant improvements in early fault prediction compared to state-of-the-art baselines. Our method establishes a new paradigm for safety-critical industrial applications requiring reliable prediction of hidden degeneration processes.

Publisher Copyright: © 2026 Owner/Author.

Time series forecasting has become a critical task in data engineering, with the volume of time series data projected to reach 180 ZB by 2025. While traditional forecasting models are typically constrained to single domains, missing opportunities for transferring temporal patterns across different domains. Through analysis, we observe that time series from different domains, despite their distinct statistical characteristics, can be fundamentally understood through temporal dependency patterns, which manifest as either long-term dependencies ( like trends and cycles) or short-term dependencies ( like fluctuations and abrupt changes). This observation motivates us to rethink cross-domain modeling from the dependency preferences perspective. We propose LSTPO, a novel framework that captures cross-domain commonalities through temporal dependency preferences and leverages a meta-learning-based approach to prevent cross-domain training forgetting. LSTPO dynamically models changes in preference over time and swiftly adapts to preference variations across different domains, enabling robust cross-domain forecasting. Through extensive experimental evaluations, we have shown that LSTPO substantially outperforms state-of-the-art forecasting methods while enhancing model transferability under few-shot learning conditions. The source code will be made publicly available upon acceptance.

This paper aims to enhance the performance of Vehicular Platooning (VP) systems integrated with Wireless Federated Learning (WFL). In highly dynamic environments, vehicular platoons experience frequent communication changes and resource constraints, which significantly affect information exchange and learning model synchronization. To address these challenges, we first formulate WFL in VP as a joint optimization problem that simultaneously considers Age of Information (AoI) and Federated Learning Model Drift (FLMD) to ensure timely and accurate control. Through theoretical analysis, we examine the impact of FLMD on convergence performance and develop a two-stage Resource-Aware Control framEwork (RACE). The first stage employs a Lagrangian dual decomposition method for resource configuration, while the second stage implements a multi-agent deep reinforcement learning approach for vehicle selection. The approach integrates Multi-Head Self-Attention and Long Short-Term Memory networks to capture spatiotemporal correlations in communication states. Experimental results demonstrate that, compared to baseline methods, the proposed framework improves AoI optimization by up to 45%, accelerates learning convergence, and adapts more effectively to dynamic VP environments on the AI4MARS dataset.

Detecting social bots is crucial for mitigating the spread of misinformation and preserving online conversation authenticity. State-of-the-art solutions typically leverage graph neural networks (GNNs) to model user representations from social relationships and metadata. However, these approaches overlook two key factors: the similarity of a user and her neighbors, as well as the coordinated behaviors of social bots, resulting in a suboptimal detection performance. To address these issues, we propose HyperScan, a novel representation learning method for social bot detection. Specifically, we introduce three effective learners to capture pair-wise, hop-wise, and group-wise relations. HyperScan learns pair-wise user representations based on social relations and user features. It then enhances user representations by building hop-wise interactions across the learned pair-wise user representations for capturing the structure-level proximity information. Subsequently, it models user representations by constructing higher-order (group-wise) relations derived from user profiles, tweets, and social relations to capture the feature-level proximity knowledge. By leveraging hop-wise interactions and higher-order relations, HyperScan significantly improves bot detection performance. Our extensive experiments demonstrate that HyperScan outperforms state-of-the-art methods on three benchmark datasets. Additional studies validate the robustness and effectiveness of each component of HyperScan.

Recently, decentralized online social networks (DOSNs) such as Mastodon have emerged quickly, bringing new opportunities for studies in user behavior modeling and multi-modal learning. However, their decentralized architecture presents two key challenges: 1) Distributed data and inconsistent access strategies across several individual instances make a unified collection difficult; 2) user-generated content (UGC) contains multiple modalities while lacking standard organization and high-quality annotation. To address these issues, we constructed FediData, a comprehensive multi-modal dataset from Mastodon. Our dataset integrates user profiles, text, images, and social interactions. To validate FediData's usefulness, we designed and analyzed several tasks and systematically evaluated the performance of existing state-of-the-art methods. Our analysis reveals the unique challenges of DOSNs and highlights the value of FediData in DOSN-related studies. We believe FediData could serve as a foundational dataset for advancing user behavior analytics, multi-modal learning, and future decentralized web research. All data and documentation are available in a Zenodo repository at https://zenodo.org/records/15621243 (DOI: 10.5281/zenodo.15621243).

We release a large-scale dataset that captures interactions between human users and CommentRobert, an LLM-based social media agent on Weibo. The dataset contains Weibo posts in which users actively mention the LLM agent account @CommentRobert, indicating that the users are interested in interacting with the platform-empowered LLM agent. The dataset contains 557,645 interactions from 304,400 unique users over 17 months. We detail our data collection methodology, user attributes, and content characteristics, underscoring the dataset's value in examining real-world human-LLM agent interactions. Our analysis offers insights into the demographic and behavioral traits of users interested in the selected LLM agent, interaction dynamics between humans and the agent, and linguistic patterns in comments. These interactions provide a unique lens through which to explore how humans perceive, trust, and communicate with LLMs. This dataset enables further research into modeling human intent understanding, improving LLM agent design, and studying the evolution of human-LLM agent relationships. Potential applications also include long-term user engagement prediction and AI-generated comment detection on social platforms. This constructed dataset is available at https://zenodo.org/records/16921462.

Spiking Neural Network (SNN) simulation involves emulating the activation and firing of spiking neurons on hardware platforms. This is a highly time-sensitive task, requiring the simulation of billions of neurons and their intercommunication within a few milliseconds. Each neuron performs a complex, interdependent multi-stage communication and computation task. We consider the task placement of SNN on supercomputers to accelerate SNN simulation. Existing task placement methods for SNN simulations have two major limitations. First, they lack the capability to handle large-scale SNNs with billions of neurons. Second, they focus primarily on optimizing communication delay, while neglecting multi-stage computation delays in SNN simulations. In this paper, we formalize the SNN Joint Multi-stage Communication and Computation Placement (SJCCP) problem. We demonstrate that SJCCP can be solved using an approximation algorithm with an approximation ratio of $O\left( {{k^2}\sqrt {\log n\log k} } \right)$, where n is the number of voxels in the SNN and k is the number of GPUs. To further reduce the time complexity of solving SJCCP in practice, we propose a novel efficient framework, FastSJP, tailored for large-scale SNN placement. Then we apply the FastSJP framework to a human brain simulation that runs a large-scale SNN model derived from authentic biological data on a supercomputer equipped with 1024 GPUs. Experimental results verify that our framework notably reduces time overhead, ranging from 17.31% to 28.45%, compared to state-of-the-art methods. Leveraging the computational power of the supercomputer, FastSJP maximizes the problem size and processing performance, significantly advancing the development of brain-inspired intelligence.

Brain simulation is an inherently highly parallel and time-sensitive task, requiring the simulation of billions of neurons and their interactions within just a few milliseconds. With the growing availability of brain data from biological research, more realistic and detailed simulations are becoming feasible. However, this also poses unprecedented challenges for parallel computing due to the extreme sparsity and heterogeneity of the emerging workloads. Efficient deployment of such workloads on modern HPC systems is critical to overcoming these challenges. We propose BMapper, a deployment framework that enables efficient parallel execution of brain simulations on supercomputers. BMapper comprises three synergistic components: BPartitioning, which introduces a novel multi-dimensional hybrid partitioning strategy to balance workloads across GPUs and reduce inter-GPU spike traffic; BPlacement, which applies deterministic spectral partitioning to minimize inter-server communication; and BRelaying, which identifies lightly loaded GPUs to assist the top-k heavily loaded ones by relaying spike traffic. These components work together to balance loads and minimize communication overhead, enabling high-speed simulation of large-scale brain models. BMapper has been deployed to simulate up to 10 billion neurons on a 1000-GPU supercomputer, achieving 25.15%–47.48% faster execution than state-of-the-art methods.

Permissioned blockchains have found widespread adoption across diverse scenarios, ensuring data authenticity and integrity. However, transaction conflicts, as an inherent performance challenge in permissioned blockchains, can significantly decrease system throughput and thus degrade its Quality of Service (QoS) under substantial transaction contention. Existing approaches mitigate conflicts typically by either aborting or blocking transactions in advance, encountering two main issues: (i) resource wastage due to transaction failure and (ii) performance degradation, particularly under large block sizes or high transaction contention. In this paper, we propose PreFabric, a novel permissioned blockchain framework that guarantees high throughput by resolving the transaction conflict problem. We first conduct a comprehensive analysis of the transaction scenarios preceding simulation execution of the endorsing phase in the blockchain system to identify potential conflict-causing situations. Then, we devise an key-locking method to prevent transaction conflicts and propose concurrency control strategies based on dependency analysis, encompassing a transaction merging mechanism, an key-renaming mechanism and concurrent validating mechanisms, to improve system throughput. The experimental results demonstrate the superior performance of our method over state-of-the-art methods, with 2.1× higher effective throughput and 0.48× lower latency.

Vertical Federated Learning (VFL) enables collaborative machine learning without the need for participants to share their raw private data. However, recent studies have uncovered privacy risks, where adversaries might reconstruct sensitive features through data leakage during the learning process. Al-though existing data reconstruction methods are effective to some extent, they exhibit limitations in VFL scenarios, as initiating an attack requires meeting more stringent conditions. To gain a comprehensive understanding of the risks of data reconstruction in VFL, this paper proposes a unified framework, the Unified InverNet Framework in VFL (UIFV), for data reconstruction under realistic black-box threat models. Within the UIFV framework, we consider four attack scenarios, strictly adhering to VFL protocols to maintain confidentiality. Experiments on four datasets show that our methods significantly outperform state-of-the-art techniques in terms of applicability and attack precision. Our work reveals severe privacy vulnerabilities within VFL systems that pose real threats to practical VFL applications, thus confirming the necessity of further enhancing privacy protection in the VFL architecture. Overall, this paper provides a thorough analysis of the risks of data reconstruction in VFL and offers important guidance to enhance the security of VFL deployments.

Collaborative inference between large cloud-hosted models and small edge-deployed models offers a promising solution for balancing the accuracy and efficiency of ML-based applications in vehicular networks. Selecting the appropriate models and their hosting nodes for performing various inference tasks plays a crucial role in collaborative inference in vehicular networks. However, existing solutions, primarily based on deep reinforcement learning (DRL), suffer critical limitations, including delayed and suboptimal decisions on model and node selection in dynamic environments. To address these challenges, we propose a dynamic model and node selection strategy for a collaborative inference framework, grounded in active inference theory. Our strategy dynamically aligns task requirements with model capabilities and node capacities by considering factors such as vehicular mobility, latency constraints, task complexity, and model accuracy. Additionally, when significant drops in inference accuracy are detected, we fine-tune and update the models deployed on both the edge and cloud, ensuring reliable and up-to-date inference. By leveraging active inference to minimize free energy through Bayesian belief updates, our framework reduces average latency by 23.2%, lowers task failure rates by 67%, and achieves superior load balancing compared to existing methods. It also demonstrates robust dynamic performance with a 5.1% failure rate under 200% traffic surges, and its hybrid update strategy maintains 85.4% accuracy after 72 hours, effectively addressing the complex and dynamic conditions of vehicular networks.

Backdoor attacks in vertical federated learning (VFL) are particularly concerning as they can covertly compromise VFL decision-making, posing a severe threat to critical applications of VFL. Existing defense mechanisms typically involve either label obfuscation during training or model pruning during inference. However, the inherent limitations on the defender's access to the global model and complete training data in VFL environments fundamentally constrain the effectiveness of these conventional methods. To address these limitations, we propose the Universal Backdoor Defense (UBD) framework. UBD leverages Label Consistent Clustering (LCC) to synthesize plausible latent triggers associated with the backdoor class. This synthesized information is then utilized for mitigating backdoor threats through Linear Probing (LP), guided by a constraint on Batch Normalization (BN) statistics. Positioned within a unified VFL backdoor defense paradigm, UBD offers a generalized framework for both detection and mitigation that critically does not necessitate access to the entire model or dataset. Extensive experiments across multiple datasets rigorously demonstrate the efficacy of the UBD framework, achieving state-of-the-art performance against diverse backdoor attack types in VFL, including both dirty-label and clean-label variants.

Federated Graph Neural Network (FedGNN) integrate federated learning (FL) with graph neural networks (GNNs) to enable privacy-preserving training on distributed graph data. Vertical Federated Graph Neural Network (VFGNN), a key branch of FedGNN, handles scenarios where data features and labels are distributed among participants. Despite the robust privacy-preserving design of VFGNN, we have found that it still faces the risk of backdoor attacks, even in situations where labels are inaccessible. This paper proposes BVG, a novel backdoor attack method that leverages multi-hop triggers and backdoor retention, requiring only four target-class nodes to execute effective attacks. Experimental results demonstrate that BVG achieves nearly 100% attack success rates across three commonly used datasets and three GNN models, with minimal impact on the main task accuracy. We also evaluated various defense methods, and the BVG method maintained high attack effectiveness even under existing defenses. This finding highlights the need for advanced defense mechanisms to counter sophisticated backdoor attacks in practical VFGNN applications.

Knowledge diversity and knowledge forgetting are two major issues in sustaining collaborative learning within heterogeneous vehicle networks. These issues become especially severe when vehicles possess varying sensing capabilities, computational resources, and domain expertise, leading to fragmented learning and unstable knowledge retention over time. To address these challenges, we propose a dual-level game-theoretic approach. We first formulate a new metric, Utility-of-Information (UoI), to characterize the features of knowledge learning, retention, and consolidation. Based on this metric, we design a game-theoretic dual-level approach, which comprises a lower-level coalition formation game where vehicles self-organize into “teacher-student” coalitions based on their UoI profiles, and an upper-level UAV resource allocation game where vehicle coalitions compete for limited communication resources. To optimize both levels of the game, we design a unified reinforcement learning-based framework that enables adaptive searching for optimization under dynamic network conditions. Experimental results demonstrate that our approach effectively addresses knowledge diversity and significantly mitigates the effects of knowledge forgetting in UAV-assisted heterogeneous vehicle networks.

Cloud-edge-terminal orchestrated computing, as an expansion of cloud computing, has sunk resources to the edge nodes and terminal equipment, which can provide high-quality services for delay-sensitive applications and reduce the cost of network communication. Due to the high volume of data generated by Internet of Things (IoT) devices and the limited storage capacities of edge nodes, a significant number of terminal devices are now being considered for utilization as storage nodes. However, because of the heterogeneous storage capacity and reliability of these hardware devices and the different data requirements of user services, the performance and storage reliability of applications deployed in cloud-edge-terminal orchestrated computing environments have become urgent problems to be solved. Especially, for a distributed storage system in these environments, it is required to ensure reliable storage of the generated data and its’ replications. In this paper, we first implement a distributed storage system and construct a data replication placement model. Then, based on the constructed model, we formulate the data replication placement problem and design a data replication placement strategy called DRPS to solve it. The DRPS covers a ranks-based replication storage node selection algorithm and a greedy load balancing algorithm, which can select appropriate hardware devices for different data requirements of services and is implemented in the data storage system to store replications and balance loads. We design extensive experiments to verify the effectiveness of DRPS. The results indicate that the proposed strategy outperforms other state-of-the-art algorithms in terms of system delay reduction by 39.9%, an increase of 43.3% in the replication numbers, a 27.5% improvement in memory utilization, and a reduction of unreliability rate by 82.0%.

Reconfigurable Intelligent Surface (RIS)-assisted uncrewed Aerial Vehicle (UAV) communications have been realized as essential to space-air-group system integration in the 6 G technology landscape. Trajectory planning plays a crucial role in RIS-assisted UAV communications to face the challenges of UAV’s limited power capacities and dynamic wireless channels. Existing solutions assume complete channel state information, focus on single-rotor UAVs, and rely heavily on time-consuming training processes for machine learning; thus, they lack applicability to deal with highly dynamic real-world scenarios. To fill these research gaps, we aim to characterize RIS-assisted UAV communications and design responsive and accurate UAV trajectory planning algorithms in this paper. We first develop a communication model with incomplete information and an energy consumption model for quadrotor UAVs. We then formulate UAV trajectory planning as an optimization problem to minimize UAV’s energy consumption while maintaining communication throughput. To solve this problem, we design an acceleration framework,FedX, for reinforcement learning (RL) solvers and present two fast trajectory planning algorithms, FedSAC and FedPPO, as instantiations of theFedXframework. Our evaluation results indicate that the proposed framework is effective and efficient–more than 3 times faster with 5 agents and 7 times faster with 10 agents than standard RL algorithms, making it suitable for using RL solvers within wireless networks and mobile computing environments. We also discuss and identify the pros and cons of our proposed framework.

Spiking Neural Networks (SNNs), due to their inherent biological plausibility and energy-saving characteristics, naturally align with the requirements of IoT services. However, current SNNs require a multi-layer structure to achieve effective applications across various fields. The multi-layer deep SNNs with massive model parameters demand computational resources, rendering them incompatible with resource-constrained IoT devices. To address this problem, in this work, a deep SNN partitioning framework called SNN-IoT is proposed to run complex SNN models on IoT devices. The SNN-IoT first partitions a full deep SNN model into smaller sub-models, leveraging the event-driven sparsity of SNNs and channel-level firing patterns to distribute filters with lower levels of spike activity onto devices with more constrained resources. The SNN model partitioning and deployment is formulated as an optimization problem and is solved using a greedy search assignment mechanism. Furthermore, a channel-wise pruning method exploits the varying degrees of channel activity, effectively reducing each sub-model's size and computational load without compromising performance. Extensive experiments conducted on four non-neuromorphic and two neuromorphic datasets have demonstrated that the SNN-IoT framework not only efficiently partitions deep SNNs and enables their deployment on IoT devices but also significantly reduces the inference latency and energy consumption for IoT services. The experiment uses 9 Raspberry Pi-4B as the IoT devices, and results show that SNN-IoT may reduce the average latency and energy consumption by about 60.7% and 49.9%, respectively, while maintaining the inference accuracy.

The increasing prevalence of blockchain technology has drawn significant attention to the need for effective Quality of Service (QoS) management in blockchain service provision. In this context, the online tuning of system configurations is pivotal for automatic blockchain services to meet QoS requirements. Past studies on configuration tuning have primarily focused on system adaptability to hardware and network environments, overlooking the dynamic nature of the highly diverse workloads, thus resulting in suboptimal system performance. This paper presents TuneChain, an online configuration auto-tuning approach for permissioned blockchain systems, which addresses the limitations of current methods, particularly in handling dynamic workloads while minimizing tuning costs. TuneChain leverages a Conflict Emergency Mechanism (CF-EM) to mitigate the impact of transaction conflicts on effective throughput and employs the Proximal Policy Optimization (PPO) algorithm coupled with a multi-instance mechanism to offer adaptive configuration recommendations tailored to diverse workloads. Additionally, TuneChain incorporates a Tuning Causal Model (TCModel) based on expert knowledge to guide decision-making in configuration tuning, thereby reducing unnecessary exploration and improving efficiency. Extensive evaluations demonstrate that TuneChain outperforms state-of-the-art approaches to configuration tuning in adapting to dynamic workloads, showcasing its efficacy in enhancing blockchain service performance.

With the rapid development of software-defined networking/network function virtualization (NFV) technologies, service function chaining (SFC) has become a key enabler for end-to-end service provisioning in future networks. In the Internet of Things (IoT), the highly dynamic nature of the network environment demands flexible and adaptive mechanisms for dynamic SFC deployment to fully utilize network resources while meeting the service requirements. Although reinforcement learning (RL) techniques offer a promising approach to dynamic SFC deployment, the learning delay of RL may limit its prompt response to sudden changes in network state and/or service demand. To address this challenge in this article, we propose to employ a deep$Q$-learning network (DQN) method for dynamic SFC deployment combined with a tidal virtual machine (TVM) control mechanism for adaptive virtual machine (VM) auto-scaling. We present a tidal DQN framework (TDQNF) that integrates the DQN method and TVM control in the ETSI NFV architecture and develop the algorithms for implementing DQN-based decisions for SFC deployment and TVM control for VM scaling. The performance of the TDQNF framework with the proposed algorithms has been evaluated through extensive simulation experiments. The obtained experimental results verify the effectiveness of the proposed scheme and indicate better performance in terms of system delay, packet loss, and load balancing in large-scale networks compared to existing methods.

Brain simulation is one of the most important measures to understand how information is represented and processed in the brain, which usually needs to be realized in supercomputers with a large number of interconnected graphical processing units (GPUs). For the whole human brain simulation, tens of thousands of GPUs are utilized to simulate tens of billions of neurons and tens of trillions of synapses for the living brain to reveal functional connectivity patterns. However, as an application of the irregular spares communication problem on a large-scale system, the sparse and imbalanced communication patterns of the human brain make it particularly challenging to design a communication system for supporting large-scale brain simulations. To face this challenge, this paper proposes a hierarchical regularized communication mechanism, HRCM. The HRCM maintains a hierarchical virtual communication topology (HVCT) with a merge-forward algorithm that exploits the sparsity of neuron interactions to regularize inter-process communications in brain simulations. HRCM also provides a neuron-level partition scheme for assigning neurons to simulation processes to balance the communication load while improving resource utilization. In HRCM, neuron partition is formulated as a k-way graph partition problem and solved efficiently by the proposed hybrid multi-constraint greedy (HMCG) algorithm. HRCM performs finer-grained neuron-level communication control while leveraging voxel-level control as the basis, thus being more effective in balancing inter-process traffic in large-scale simulations. The hierarchical characteristics of the finer-grained communication control are considered by the problem formulation and algorithm design in HRCM. HRCM has been implemented in human brain simulations at the scale of up to 86 billion neurons running on 10000 GPUs. Results obtained from extensive simulation experiments verify the effectiveness of HRCM in significantly reducing communication delay, increasing resource usage, and shortening simulation time for large-scale human brain models.

Vertical Federated Learning (VFL) facilitates collaboration on model training among multiple parties, each owning partitioned features of the distributed dataset. Although backdoor attacks have been found as one of the main threats to FL security, research on backdoor attacks in VFL is still in the infant stage. Existing methods for VFL backdoor attacks rely on predicting sample pseudo-labels using approaches such as label inference, which require substantial additional information not readily available in practical FL scenarios. To evaluate the practical vulnerability of VFL to backdoor attacks, we present a target-efficient clean backdoor (TECB) attack for VFL. The TECB approach consists of two phases – i) Clean Backdoor Poisoning (CBP) and Target Gradient Alignment (TGA). In the CBP phase, the adversary trains a backdoor trigger and poisons the model during VFL training. The poisoned model is further fine-tuned in the TGA phase to enhance its efficacy in complex multi-classification tasks. Compared to the existing methods, the proposed TECB achieves a highly effective backdoor attack with very limited information about the target class samples, which is more practical in typical VFL settings. Experimental results verify the superior performance of TECB, achieving above 97% attack success rate (ASR) on three widely used datasets (CIFAR10, CIFAR100, and CINIC-10) with only 0.1% of target labels known, which outperforms the state-of-the-art attack methods. This study uncovers the potential backdoor risks in VFL, enabling the development of secure VFL applications in areas like finance, healthcare, and beyond. Source code is available at: https://github.com/13thDayOLunarMay/TECB-attack

Distributed machine learning methods like Federated Learning (FL) and Split Learning (SL) meet the growing demands of processing large-scale datasets under privacy restrictions. Recently, FL and SL are combined in hybrid SLFL (SFL) frameworks to exploit both methods’ advantages to facilitate ubiquitous intelligence in the Internet of Things (IoT), for example, smart finance. Despite its significant impact on the performance and costs of SFL, model decomposition that splits an ML model into the client-server pair has not been sufficiently studied, especially for SFL in a large-scale dynamic IoT environment. In this paper, we propose a new SFL framework HSFL with a lightweight model decomposition method to offload a part of model training to the edge server. Specifically, we develop a method for estimating the training latency of HSFL and designed a metric for measuring privacy leakage in HSFL, based on which we formulate model decomposition in HSFL as an optimization problem with privacy protection as a constraint. Then, we transform the formulated problem into a contextual bandit problem and design an efficient algorithm to solve it. We have conducted thorough evaluations of the proposed HSFL framework through extensive experiments on a prototype testbed and a simulation platform. The experimental results validate the superiority of HSFL over the state-of-the-art benchmarks in terms of training latency, efficiency, scalability, and privacy protection.

While edge computing has the potential to offer low-latency services and overcome the limitations of traditional cloud computing, it presents new challenges in terms of trust, security, and privacy (TSP) in Internet of Things environments. Cooperative edge computing (CEC) has emerged as a solution to address these challenges through resource sharing among edge nodes. However, for multi-infrastructure providers, incentive and trust mechanisms among edge nodes are crucial technical issues that must be addressed alongside system latency and reliability to meet performance requirements. In this article, we propose a blockchain-assisted intelligent edge cooperation system (BIECS) to systematically solve these issues. By leveraging blockchain technology, we construct trust among edge nodes and employ an incentive mechanism for resource sharing among multi-infrastructure providers. We formulate the system performance optimization as a multiobjective joint optimization problem and solve it efficiently through a two-stage strategy for selecting edge nodes. We first design an improved long short term memory (LSTM) model for resource prediction and then select edge nodes for executing offloaded tasks and handling the corresponding blockchain process related to each task execution. To evaluate the performance of BIECS, we implement the system based on Hyperledger Fabric and design extensive experiments. Our proposed system achieves better performance in terms of system delay, throughput, and resource utilization compared to state-of-the-art schemes for edge cooperation.

Federated learning (FL) offers a promising approach to efficient machine learning with privacy protection in distributed environments, such as Internet of Things (IoT) and mobile-edge computing (MEC). The effectiveness of FL relies on a group of participant nodes that contribute their data and computing capacities to the collaborative training of a global model. Therefore, preventing malicious nodes from adversely affecting the model training while incentivizing credible nodes to contribute to the learning process plays a crucial role in enhancing FL security and performance. Seeking to contribute to the literature, we propose a blockchain-empowered secure and incentive FL (BESIFL) paradigm in this article. Specifically, BESIFL leverages blockchain to achieve a fully decentralized FL system, where effective mechanisms for malicious node detections and incentive management are fully integrated in a unified framework. The experimental results show that the proposed BESIFL is effective in improving FL performance through its protection against malicious nodes, incentive management, and selection of credible nodes.

Inter-process communications form a performance bottleneck for large-scale brain simulations. The sparse and imbalanced communication patterns of human brain make it particularly challenging to design a communication system for supporting large-scale brain simulations. In this paper, we tackle the communication challenges posed by large-scale brain simulations with sparse and imbalanced communication patterns. We design a virtual communication topology with a merge and forward algorithm that exploits the sparsity to regularize inter-process communications. To balance the communication loads of different processes, we formulate voxel partition in brain simulations as a k-way graph partition problem and propose a constrained deterministic greedy algorithm to solve the problem effectively. We conducted extensive simulation experiments for evaluating the performance of the proposed communication scheme and found that the proposed method may significantly reduce communication overheads and shorten simulation time for large-scale brain models.

Although the emerging edge computing paradigm offers a promising approach to overcoming some limitations of conventional cloud computing, the heterogeneous edge nodes with highly diverse system capacities bring new challenges to service provisioning especially for latency-sensitive services. Cooperative edge computing (CEC) has been proposed for facing such challenges through resource sharing among edge nodes. However, some technical issues must be fully addressed to make CEC effective, among which incentive and trust mechanisms and performance optimization are crucial for latency-sensitive service provision. In this paper, we design a novel blockchain-based intelligent edge cooperation system named BIECS to tackle these challenges systematically. BIECS provides incentive to edge nodes for resource sharing and enables trust among cooperative nodes upon a distributed platform leveraging the blockchain technology. In order to optimize system performance for meeting the requirements of latency-sensitive services, we propose a two-stage strategy for node selection in BIECS that chooses the most appropriate edge nodes for executing offloaded tasks and recording related transactions in the blockchain. We also implemented a prototype of BIECS based on Hyperledger Fabric and conducted extensive experiments for evaluating the performance of BIECS. The obtained experiment results verify that the proposed BIECS achieves better performance in system delay and throughput compared to the state-of-the-art methods for edge cooperation.

The wide deployment of advanced robots with industrial IoT (IIoT) technologies in smart factories generates a large volume of data during production and a wide variety of data processing workloads are launched to maintain productivity and safety of smart manufacture. The emerging fog computing paradigm offers a promising solution to enhancing data processing performance in a smart factory environment while on the other hand brings in new challenges to resource management, which call for a more effective approach for recommending resource configurations to heterogeneous workloads. In this paper, we propose an Optimized Recommendations of Heterogeneous Resource Configurations (ORHRC) model that employs machine learning techniques to provide resource configuration recommendations for the heterogeneous workloads in a fog computing-based smart factory environment. ORHRC learns a recommendation model by leveraging the operating characteristics and execution time of workloads on fog servers with different configurations. We also design a decision model in ORHRC to further improve prediction accuracy and reduce operational overheads. Experiment results show that ORHRC outperforms the state of art configuration recommendation methods in terms of average prediction accuracy.Note to Practitioners—The various data processing workloads in a smart factory environment need to be processed by the computational resources with optimal configurations for meeting their performance requirements. In this paper, we employ machine learning technologies for enabling automatic recommendation of resource configurations to heterogeneous workloads. Specifically, we develop an Optimized Recommendations of Heterogeneous Resource Configurations (ORHRC) model that can identify the optimal resource configurations for various workloads. We also conducted extensive experiments that verify the effectiveness of the proposed ORHRC model.

Anomaly detection is crucial to the reliability and safety of rail transit systems. The rapid development of Internet of Things (IoT) and cloud technologies together with recent advances in machine learning offered various cloud-based data-driven approaches to automatic anomaly detection. However, the challenges introduced by the different types of equipment in rail transit systems with highly diverse data distributions and the lack of labeled anomaly data have not been sufficiently addressed. In this article, we attempt to cope with such challenges by proposing an improved long short term memory (LSTM)-based time-series anomaly detection scheme. The key elements of the proposed scheme include an improved LSTM model that may achieve more accurate time-series prediction for various rail transit devices and a method for determining an appropriate error threshold for detecting anomalies based on the prediction errors. In order to further enhance anomaly detection performance, we also propose a pruning algorithm for reducing the number of false anomalies. Our method does not rely on scarce anomaly labels but dynamically determines a threshold of prediction errors to identify anomalies; therefore, it overcomes the challenge of the extremely uneven distribution of rail transit data. We conducted extensive experiments in a real metro operation environment for performance evaluation. The experiment results prove the effectiveness of the proposed scheme and show a superior performance of the scheme compared to existing anomaly detection methods.

We investigate how to provide Quality-of-Service (QoS) for diversified video flows. We design a fine-grained video traffic control mechanism that integrates traffic classification with path selection for video flows within the framework of SDN. For the design, we present a category-theoretic ontology log (olog) diagram model, which provides a novel perspective on the interdependency among various system components. For the video traffic classification, we first evaluate various machine learning classifiers in terms of their performance and then chose the most effective one to be the first module. For the path selection, we devise a multi-constrained QoS routing strategy by restructuring a state-of-the-art graph algorithm, combine it with the${k}$-shortest path algorithm, and deploy this strategy as another video traffic control module. We implemented a prototype of the proposed mechanism on the SDN emulator Mininet, and we evaluate its effectiveness using the performance results obtained.

Federated Learning (FL) deployed in edge computing may achieve some advantages such as private data protection, communication cost reduction, and lower training latency compared to cloud-centric training approaches. The Anything-as-a-Service (XaaS) paradigm, as the main service provisioning model in edge computing, enables various flexible FL deployments. On the other hand, the distributed nature of FL together with the highly diverse computing and networking infrastructures in an edge environment introduce extra latency that may degrade FL performance. Therefore, delay performance evaluation on edge-based FL systems becomes an important research topic. However, XaaS-based FL deployment brings new challenges to performance analysis that cannot be well addressed by conventional analytical approaches. In this paper, we attempt to address such challenges by proposing a profile-based modeling and analysis method for evaluating delay performance of edge-based FL systems. The insights obtained from the modeling and analysis may offer useful guidelines to various aspects of FL design. Application of network calculus techniques makes the proposed method general and flexible, thus may be applied to FL systems deployed upon the heterogeneous edge infrastructures.

Edge computing as a highly distributed multi-tenant computing system relies on its effective interactions with the underlying 5G network to achieve its advantages in service provisioning. On the other hand, edge computing is also transforming 5G network via deploying more computing capabilities at network edge. In this paper, we advocate a holistic vision of service orchestration to facilitate integration of edge computing and 5G network. We attempt to sketch a big picture of the state of the art research enabling the integrated network-edge service architecture. We also discuss technical challenges and identify opportunities for future research in this area.

Mobile-edge computing provisions computing and storage resources by deploying edge servers (ESs) at the edge of the network to support ultralow delay and high bandwidth services. To ensure QoS of latency-sensitive services in vehicular networks, service migration is required to migrate data of the ongoing services to the closest ES seamlessly when users move across different ESs. To achieve seamless service migration, path selection is proposed to obtain one or more paths (consisting of several switches and ESs) to transfer service data. We focus on the following problems about path selection: 1) where to implement path selection? 2) how to coordinate interests of mobile users (i.e., vehicles) and network providers since they have conflicting interests during path selection? and 3) how to ensure seamless service migration during the migration of vehicles? To address the above problems, this article investigates path selection for seamless service migration. We propose a path-selection algorithm to jointly optimize both interests of the network plane (i.e., the cost for network providers) and service plane (i.e., QoE of users). We first formulate it as a multiobjective optimization problem and further prove theoretically that the proposed algorithm can give aweakly Pareto-optimal solution. Moreover, to improve the scalability of the proposed algorithm, a distance-based filter strategy is designed to eliminate undesired switches in advance. We conduct experiments on two synthesized data sets and the results validate the effectiveness of the proposed algorithm.

The recent developments in networking research leverage the principles of virtualization and service-orientation to enable fundamental changes in network architecture, which forms a trend of network cloudification that enables network systems to be realized using cloud technologies and network services to be provisioned following the cloud service model. On the other hand, the latest progress in cloud and fog computing has made networking an indispensable ingredient for cloud/fog service delivery. Convergence of networking and cloud/fog computing technologies enables unification of network and cloud/fog service provisioning, which has become an active research area that attracts interest from both academia and industry. In this paper, we introduce the notion of network-cloud/fog service unification and propose an architectural framework for unified network-cloud/fog service provisioning. Then we present a survey that reflects the state of the art of research on enabling network-cloud/fog service unification. We also discuss challenges to realizing such unification and identify some opportunities for future research, with a hope to arouse the research community's interest in this exciting interdisciplinary field.

The crucial role of networking in cloud computing calls for federated management of both computing and networking resources for end-to-end service provisioning. Application of the Service-Oriented Architecture (SOA) in both cloud computing and networking enables a convergence of network and cloud service provisioning. One of the key challenges to high performance converged network-cloud service provisioning lies in composition of network and cloud services with end-to-end performance guarantee. In this paper, we propose a QoS-aware service composition approach to tackling this challenging issue. We first present a system model for network-cloud service composition and formulate the service composition problem as a variant of Multi-Constrained Optimal Path (MCOP) problem. We then propose an approximation algorithm to solve the problem and give theoretical analysis on properties of the algorithm to show its effectiveness and efficiency for QoS-aware network-cloud service composition. Performance of the proposed algorithm is evaluated through extensive experiments and the obtained results indicate that the proposed method achieves better performance in service composition than the best current MCOP approaches.

The widespread deployment of web services and rapid development of big data applications bring in new challenges to web service compositions in the context of big data. The large number of web services processing a huge amount of diverse data together with the complex and dynamic relationships among the services require automatic composition of semantic web services to be performed quickly, thereby demanding more efficient service composition algorithms. In this paper, we investigate the issue of web service composition in big data environments by proposing novel composition algorithms with low time-complexity. Specifically, we decompose the service composition into three stages - construction of parameter expansion graphs, transformation of service dependence graphs, and backtracking search for service compositions. Based on the parameter expansion strategies, we then propose two efficient semantic web service composition algorithms and analyze their time complexity. We also conduct comparison experimentally to evaluate the efficiency of the algorithms and validate their effectiveness using a big data (service composition) set.

Multicast routing that meets multiple quality of service constraints is important for supporting multimedia communications in the Internet of Things (IoT). Existing multicast routing technologies for IoT mainly focus on ad hoc sensor networking scenarios; thus, are not responsive and robust enough for supporting multimedia applications in an IoT environment. In order to tackle the challenging problem of multicast routing for multimedia communications in IoT, in this paper, we propose two algorithms for the establishing multicast routing tree for multimedia data transmissions. The proposed algorithms leverage an entropy-based process to aggregate all weights into a comprehensive metric, and then uses it to search a multicast tree on the basis of the spanning tree and shortest path tree algorithms. We conduct theoretical analysis and extensive simulations for evaluating the proposed algorithms. Both analytical and experimental results demonstrate that one of the proposed algorithms is more efficient than a representative multiconstrained multicast routing algorithm in terms of both speed and accuracy; thus, is able to support multimedia communications in an IoT environment. We believe that our results are able to provide in-depth insight into the multicast routing algorithm design for multimedia communications in IoT.

Recent development in Cloud and networking technologies have stimulated unification of network and Cloud service provisioning, in which service composition plays a crucial role. While encouraging progress has been made toward network-Cloud service composition, the impact of correlated network and Cloud services on the QoS of composite services, however, has not been sufficiently studied. In this paper, we address the challenging problem of QoS correlation-aware network and Cloud service composition. Specifically, we formulate this problem as a multi-constraint optimal path problem and propose a novel algorithm to solve it. We also evaluate the performance of the proposed algorithm with extensive simulations. The experimental results show that the proposed algorithm is effective and efficient and it is able to yield service composition solutions with better QoS guarantees through considering QoS correlations among different services.

Software Defined Networking (SDN), the novel paradigm of decoupling the control logic from packet forwarding devices, has been drawing considerable attention from both academia and industry. As the latency between a controller and switches is a significant factor for SDN, selecting appropriate locations for controllers to shorten the latency becomes one grand challenge. In this paper, we investigate multi-controller placement problem from the perspective of latency minimization. Distinct from previous works, the network partition technique is introduced to simplify the problem. Specifically, the network partition problem and the controller placement problem are first formulated. An optimized K-means algorithm is then proposed to address the problem. Extensive simulations are conducted and results demonstrate that the proposed algorithm can remarkably reduce the maximum latency between centroid and their nodes compared with the standard K-means. Specifically, the maximum latency can reach 2.437 times shorter than the average latency achieved by the standard K-means.

Cloud computing has emerged as a new computing paradigm and its economics has opened up a new research area. Though progress has been made toward address competitions among Cloud service providers (CSPs) or among network service providers (NSPs), few studies have focused on the relationship between CSPs and NSPs. In this paper, we investigate this problem and present a new economic model to characterize the competition between CSPs and NSPs. We then conduct thorough theoretical analysis and numeric experiments to validate the proposed model. The results show that the replacement coefficient, connection rate, service coefficient, the equilibrium will affect the market share and the profit of CSPs and NSPs. Through this study, we believe that the developed economic model is general and practical, thus it is applicable to model the Cloud computing market.

Resource allocation plays a critical role in implementing D2D communications underlaying a cellular network. Game-based approaches are recently proposed to address the resource allocation issue. Most existing approaches employ deterministic game models while implicitly assuming that each player in the game is completely willing to exchange transmission parameters with other players. Thus each player knows the complete information of all others. However, this assumption may not be satisfied in practice. For example, users may be reluctant to disclose all their parameters to peers. In this paper, we fully consider this scenario, i.e., players have incomplete information of others, and investigate the resource allocation problem for multicell D2D communications where a D2D link utilizes common resources of multiple cells. To attack this problem, a game-theoretic approach under the incomplete information condition is proposed. Specifically, we characterize the Base Stations (BSs) as players competing for resource allocation quota from the D2D demand, formulate the utility of each player as payoff from both cellular and D2D communications leasing the resources, and design the strategy for each player that is determined based on prior probabilistic payoff information of other players. We conduct extensive simulations to examine the proposed approach and the results demonstrate that the utility, sum rate, and sum rate gain of each player under the incomplete information condition are surprisingly higher than the counterparts under the complete information condition.

Software Defined Network (SDN) may significantly enhance network and service management by enabling separated control and data planes. The centralized OpenFlow controller with a global vision of network states offers a promising approach to realizing flow-based admission control for supporting Quality of Service (QoS) provisioning in SDN. However, per-flow process brings in challenges to scalability of OpenFlow-based SDN. Flow aggregation has been explored as an effective method to address this issue. In this paper, we investigate admission control with flow aggregation for QoS provisioning in SDN. Specifically we propose a model for admission control with flow aggregation and develop the analysis techniques for determining the required amounts of bandwidth and buffer space at OpenFlow-enabled switches for meeting performance requirements in delay and packet loss. Network calculus is applied in our modeling and analysis; which makes our method applicable to general OpenFlow-based SDNs with various implementations. Numerical experiment results are also provided to evaluate effectiveness of the developed modeling and analysis techniques.

The large amount of data collected in the Internet of Things (IoT) need to be transmitted to servers for processing in order to provide various services. Due to the limited amount of resources in IoT, including network bandwidth, node processing abilities, and server capacities, congestion control in IoT plays a crucial role for meeting service performance requirements. In this paper, we propose a model for congestion control in IoT with an improved Random Early Discard (IRED) algorithm. We employ queueing theory to analyze the performance of the proposed control mechanism. We also conduct extensive simulations to evaluate performance of the proposed control and compare it with regular RED algorithm. Our analysis and simulation results show that the proposed control achieves comparable delay performance and better throughput performance compared to standard RED. The simple control mechanism of IRED makes it more suitable to be implemented in IoT.

The Internet of Things (IoT) has been realized as one of the most promising networking paradigms that bridge the gap between the cyber and physical world. Developing green deployment schemes for IoT is a challenging issue since IoT achieves a larger scale and becomes more complex so that most of the current schemes for deploying wireless sensor networks (WSNs) cannot be transplanted directly in IoT. This paper addresses this challenging issue by proposing a deployment scheme to achieve green networked IoT. The contributions made in this paper include: 1) a hierarchical system framework for a general IoT deployment, 2) an optimization model on the basis of proposed system framework to realize green IoT, and 3) a minimal energy consumption algorithm for solving the presented optimization model. The numerical results on minimal energy consumption and network lifetime of the system indicate that the deployment scheme proposed in this paper is more flexible and energy efficient compared to typical WSN deployment scheme; thus is applicable to the green IoT deployment.

Network Calculus (NC) is a powerful means to provide deep insight for flow problems in network performance analysis. Multi-priority scheduling as one of the fundamental models in NC has become an active research topic recently. However, existing works consider neither the arrival interval of the flows nor their arrival orders; thus limiting their applications to only a few delicate scenarios. In this paper, we address these two issues and propose a novel multi-priority model based on the non-preemptive priority scheduling. We derive the theoretical formulation for the service curve under this model, and then obtain the upper bounds of delay and backlog for multi-priority scheduling. We also use two representative case studies to show the correctness and effectiveness of the proposed model. The theoretical analysis is further validated by the numerical experiments. In addition, we discuss the factors that may affect the delay and backlog bounds according to the numerical results.

Cloud computing is one of the most significant latest efforts in the field of information technology, which may change the way how information services are provisioned. In a Cloud environment, different types of resources need to be virtualized as a collection of Cloud services using virtualization technology. End-users in the Cloud are usually provided with customized Cloud services that involve not only different kinds of computing services but also the networks interconnecting those computing services. Therefore, a set of Cloud computing services and the networking services should be modeled as a composite customized Cloud service. In this paper, we present an improved model for Cloud service provisioning based on our previous Network-Cloud proposal, and propose a procedure with several QoS-aware service selection algorithms for composing different services offered by a Cloud. Our analysis with numerical experiments show that the presented algorithms can select services appropriately that deal with different requirements of service provisioning.

Cloud computing is an emerging computing paradigm that may change the way how information services are provisioned. Network virtualization plays a crucial role in a Cloud environment for abstracting and virtualizing various network infrastructures as services. Therefore virtual network services should be integrated with Cloud service to form the composite Cloud service. However, little research has focused on modeling and optimization of network virtualization in Cloud service provisioning to end users. In this paper, we model the Cloud service provisioning feature in virtualization-based Cloud computing, and propose an exact algorithm for QoS-aware service composition to optimize user's experiences for Cloud service access. Our theoretical analysis indicates that the proposed algorithm is light-weighted and cost-effective. We also compare the proposed algorithm against a variant of the best-known QoS routing algorithm experimentally. The results show that the proposed algorithm has better performance both in execution time and finding solution. We believe that the modeling technique and the algorithm presented in this paper are general and effective, thus are applicable to practical Cloud computing systems.

The crucial role that networking plays in Cloud computing calls for a holistic vision that allows combined control, management, and optimization of both networking and computing resources in a Cloud environment, which leads to a convergence of networking and Cloud computing. Network virtualization is being adopted in both telecommunications and the Internet as a key attribute for the next generation networking. Virtualization, as a potential enabler of profound changes in both communications and computing domains, is expected to bridge the gap between these two fields. Service-Oriented Architecture (SOA), when applied in network virtualization, enables a Network-as-a-Service (NaaS) paradigm that may greatly facilitate the convergence of networking and Cloud computing. Recently the application of SOA in network virtualization has attracted extensive interest from both academia and industry. Although numerous relevant research works have been published, they are currently scattered across multiple fields in the literature, including telecommunications, computer networking, Web services, and Cloud computing. In this article we present a comprehensive survey on the latest developments in service-oriented network virtualization for supporting Cloud computing, particularly from a perspective of network and Cloud convergence through NaaS. Specifically, we first introduce the SOA principle and review recent research progress on applying SOA to support network virtualization in both telecommunications and the Internet. Then we present a framework of network-Cloud convergence based on service-oriented network virtualization and give a survey on key technologies for realizing NaaS, mainly focusing on state of the art of network service description, discovery, and composition. We also discuss the challenges brought in by network-Cloud convergence to these technologies and research opportunities available in these areas, with a hope to arouse the research community's interest in this emerging interdisciplinary field.