ABSTRACT Deploying defense strategies in dispersed computing consumes limited resources, a challenge exacerbated when nodes have only partial information about the system state. This article proposes a security defense strategy for dispersed computing based on Backward Mean Field Games. We first analyze the problem of limited node perception ability during attacks, and construct a backward stochastic differential equation to model the evolution of node resource states. We define an individual cost function intended to optimize resource consumption for the defense strategy. Then we find the optimal decentralized defense strategy and prove that it is ‐Nash equilibrium in the limit system. Finally, simulation experiments validate the strategy's effectiveness, demonstrating that the average system state rapidly stabilizes, and individual nodes robustly track this mean‐field trajectory toward their security targets, even under local attacks. These findings confirm that the strategy effectively guides nodes toward their terminal security targets, highlighting the strategy's good performance and robustness in balancing security needs against resource consumption.

Abstract Vehicular networks increasingly necessitate a robust paradigm that harmonizes high-performance multi-task optimization with stringent data transmission privacy. Nevertheless, current research often struggles to achieve an ideal equilibrium between rigorous security, efficient coordination logic, and the constrained computational capacities of on-board units. To surmount these hurdles, this paper proposes a homomorphic encryption-based privacy preservation for adaptive quantum cross-task optimization (QHE-PSO). The proposed scheme synergistically integrates localized identity authentication, homomorphic fitness appraisal, and a cross-domain strategy migration mechanism. By managing encrypted particle swarms in distinct local regions where particles represent specific strategy configurations, QHE-PSO implements a secure migration protocol to facilitate seamless multi-task coordination. Extensive experimental evaluations confirm that QHE-PSO delivers a superior balance of cryptographic resilience and optimization efficacy compared to state-of-the-art benchmarks.

Abstract High-precision classification of encrypted traffic plays an important role in ensuring the reliability and safety of intelligent connected vehicles. However, the communication environment of vehicles is affected by complex traffic scenarios and changing external environments, which introduces noise into the observed traffic (e.g., padding artifacts and retransmission bursts). In addition, there is a strong similarity between different service categories. Therefore, existing encrypted traffic classification techniques are not applicable. To overcome these challenges, we propose SpACNet, a collaborative CNN-Transformer dual-path spectrum sensing classification network. Specifically, in addition to using stream sequence information, SpACNet also uses layered multi-scale spectrum recalibration technology and gated axial self-attention mechanism for frequency-domain information to suppress the influence of aliasing artifacts and noise. In terms of feature fusion, orthogonal constrained dynamic tensors and gating mechanisms are used to integrate and balance time-domain, frequency-domain tensors, and interaction tensors. We evaluate SpACNet and three advanced baseline methods based on public and real-world datasets. The results show that SpACNet outperforms existing methods and demonstrates robust performance on datasets containing highly similar traffic categories. In addition, a series of ablation experiments is conducted to demonstrate the advanced nature of the proposed method.

Satellite edge computing offers promising solutions for extending the coverage of terrestrial networks, particularly in remote and harsh environments. By offloading ground data to satellites for processing, this paradigm enables real-time data handling in non-terrestrial networks (NTNs). However, due to limited onboard resources and dynamic task requirements from Internet of Things (IoT) devices, online energy management becomes a critical challenge that hinders the scalability and deployment of satellite edge computing systems. In this paper, we propose an online energy management framework based on satellite-edge collaboration. A queue-based collaboration scheme is designed to coordinate satellites in handling tasks with random arrival patterns. Building upon this scheme, we formulate a joint optimization problem that integrates transmission resource allocation, computational resource assignment, power control, routing strategies, and collaboration policies, aiming to minimize the energy consumption of the satellite network. Given the dynamic, complex, and distributed nature of the problem, we present a Lyapunov-based multi-agent deep reinforcement learning (MADRL) algorithm. Specifically, we first transform the long-term stochastic optimization problem into a sequence of deterministic subproblems using the Lyapunov theory. Sub-sequently, each subproblem is decomposed into a resource allocation subproblem and an edge collaboration subproblem. Correspondingly, we devise a MADRL-based algorithm for edge collaboration and a Lagrangian multiplier iteration (LMI)-based algorithm for resource allocation. Finally, the overall problem is iteratively optimized using the block coordinate descent (BCD) framework. Simulation results demonstrate that the proposed approach achieves significant performance improvements over both baseline methods and several state-of-the-art pure deep reinforcement learning (DRL) approaches.

Edge collaboration has emerged as a promising paradigm for Internet of Things (IoT) applications. However, achieving efficient cooperation among these server nodes still faces several critical challenges, including 1) secure node interaction, 2) online task scheduling, and 3) heterogeneous resource management. Unfortunately, most existing solutions address these issues in isolation, lacking an integrated framework that jointly considers security, task scheduling, and resource management. To address these limitations, this paper proposes a blockchain-based online collaboration framework for IoT, where blockchain serves as a trusted top-layer management platform to ensure secure information sharing and resource management. In the proposed framework, we introduce two dynamic queues to effectively manage randomly arriving tasks and develop an online collaboration mechanism tailored for heterogeneous edge servers. Furthermore, we formulate a long-term system utility maximization problem by jointly optimizing collaboration strategies, resource allocation, and block producer selection, subject to queue stability and security constraints. Due to the coupling among decision variables and across time slots, solving the optimization problem directly is challenging. Therefore, we design a novel Lyapunov-based algorithm that integrates convex optimization theory with deep reinforcement learning (DRL), significantly improving the solving efficiency. Extensive simulations demonstrate that the proposed method and algorithm outperform conventional baseline methods and pure DRL-based approaches in terms of system utility, stability, and security performance, making it a promising solution for secure and efficient edge collaboration in dynamic IoT environments.

Abstract Nowadays, the development of Artificial Intelligence of Things (AIoT) is advancing rapidly, and intelligent devices are increasingly exposed to more security risks on the network. Deep learning‐based intrusion detection is an effective security defence approach. Federated learning (FL) is capable of enabling deep learning models to be trained on local clients without uploading their data to a central server. This paper proposes a novel federated learning aggregation algorithm called fed‐dynamic gravitational search algorithm (Fed‐DGSA), which incorporates the GSA algorithm to optimize the weight updating process of FL local models. During the updating process, the decay rate of the gravity coefficient is optimized and random perturbations and dynamic weights are introduced to ensure a more stable and efficient FL aggregation process. The experimental results show that the detection accuracy of Fed‐DGSA has reached about 97.8%, and it is demonstrated that the model trained using Fed‐DGSA achieves higher accuracy compared to Fed‐Avg.

When degradation occurs in a dispersed computing network, mitigating the persistent effects of failures and improving the disposal efficiency is an open problem. However, the occurrence of failed nodes in a dispersed computing network is a random and low-probability incident. Further, the resilient resources for emergency allocation are from devices with complex spatial locations in practice. These factors pose challenges to the resource allocation problem using resilience mechanisms. In this article, we explore and analyze a resilience mechanism for dispersed computing networks as an optimization model. We investigate a resilience-aware dynamic resource allocation model to cope with a degraded dispersed computing network and obtain better emergency response at a lower cost. The uncertainties of node failures are uniquely explored to capture failure nodes more precisely and initiate the resilience mechanism for such nodes. In addition, we propose a novel approach to deal with the dynamic and complex coupling characteristics of decision variables in the model. This approach incorporates the induced artificial fish swarm algorithm with dynamic system simulation to generate and improve the scheme for the allocation of resilient resources. Finally, numerical simulation results verify the improved performance of our model and the effectiveness of the algorithm.

Crowdsourcing has found a wide variety of applications, including spectrum sensing, traffic monitoring, as well as data annotation for machine learning based data analytics. To improve data accuracy and cost-effectiveness, workers’ data quality can be learned from their data in an online manner, which can be used for task assignment and data aggregation. However, crowdsourcing is vulnerable to data poisoning attacks, where the attacker reports malicious data to reduce aggregated data accuracy. In this paper, we study malicious data attacks on dynamic crowdsourcing where tasks are assigned and performed sequentially, and we explore online quality learning as a defense mechanism against the attack by finding malicious workers with low quality. We first focus on the asymptotic setting where workers’ quality is accurately learned by the requester, based on which we then turn to the general non-asymptotic setting where the quality is estimated online with errors. For each setting, we first characterize the conditions under which the attack strategy can effectively reduce the aggregated data accuracy. Our results show that the malicious noise variance needs to be within a certain range for the attack to be effective. Then we analyze the harm of effective attack strategies. It reveals that the regret of the online quality learning algorithm can be substantially increased from$\mathcal {O}(\log ^2T)$(upper bound) to$\Omega (T)$(lower bound) due to effective attacks. To further mitigate the attack, we also study median and maximum influence of estimation based data aggregation as defense mechanisms. Our results provide useful insights on the impacts of data poisoning attacks when online quality learning is used to defend against the attack. We evaluate the proposed attacks and defenses via extensive simulation results based on real-world data, which demonstrate the effectiveness of the attacks and defenses.

The combination of Internet of Things (IoT) and artificial intelligence (AI) technology plays an important role in many fields, especially in the field of psychology and medical treatment. This work is mainly to study an affective robotics that can serve humans emotionally based on the IoT and AI technology. The design of affective robotics is important to understand the underlying mechanisms of human behaviors in real life. These mechanisms mainly include human nonverbal behaviors and affective states, which are important but difficult to be precisely modeled. To address this challenge, we introduce a human–robot interaction (HRI) architecture, including emotion recognition, affective computing, emotion diagnosis, and emotion control. First, we propose a system model based on HRI between affective robotics and human, in order to enhance the emotional service. Then, we develop a dynamical model with affective computing and control, where we provide a mathematical formulation method based on stochastic differential equations to quantify the emotional state. Furthermore, we perform the dynamic behavior analysis of the existence, boundedness, and stability of the model solution comprehensively. Numerical results are provided to demonstrate the validity and feasibility of the proposed design techniques.

The fusion of edge computing and artificial intelligence (AI) technology is a key enabler for the smart Internet of Things (IoT). However, these two emerging paradigms face many issues for their integration, such as data storage structure, model generation algorithms, and cloud-edge collaboration mechanisms. Moreover, edge computing is not ready for supporting AI and can be enabled to support AI via some basic network functions related to Quality of Experience (QoE), such as passive computation offloading and content caching. In this article, we present an intelligent cooperative edge (ICE) computing in IoT networks to achieve a complementary integration of AI and edge computing. The AI-related modules of edge computing are redesigned for distributing AI's core functions from the cloud to the edge. IoT-generated data are differentiated as user-private data preserved locally in IoT devices, edge-private data isolated on the edge and public data uploaded to the cloud. Therefore, a cloud-scale machine learning model can be generated, followed by privacy-preserving transfer learning running on each edge, which also has data updated more frequently that enables the model's incremental learning. The model distribution is accomplished through lightweight deployment pipelines consisting of cloud compression and edge reconstruction. Conversely, some key issues of edge computing, such as the computation offloading and content caching, achieve a better solution using the localized AI. We perform the prototype-based evaluation, which indicates that the ICE computing architecture enables a benign combination of AI and edge computing.

Mobile fog computing (MFC) is an emerging paradigm that extends cloud computing (CC) by adding a new layer between the cloud and its end users.With the cloud-aware MFC, the cloud can pre-push certain important resources to the fog to reduce the networking latency and release the traffic burden over the links.e end user then is able to perform offline computing on the fog layer so that only the important results need to be delivered to and stored in the cloud.Moreover, the dense geographical deployment of fog servers enables the system to be aware of the end user's location.erefore, some location-sensitive applications could be well supported by the fog-aided cloud systems.Note that the cloud-aware MFC is different from the mobile edge computing (MEC), another promising technology for overcoming the shortcomings of CC, since MFC is able to jointly work with the cloud, but MEC is usually defined by the exclusion of CC.Specifically, in MEC, computing applications, data, and services are pushed away from the centralized nodes to the network edge, which enables network edge to run in an isolated environment from the rest of the network and provides access to local resources and data.In contrast, MFC provides not only a systemlevel horizontal architecture but also a new way to distribute, orchestrate, and manage secure resources across the network rather than just performing computing at the network edge.How to design efficient system architectures, transmission strategies, and protocols for MFC and how to efficiently analyze and evaluate the system performance are very important and essential.ese topics have carved out a new area rich in research and innovation potential.is special issue aims to address all these topics and invite contributions from worldwide leading researchers.

Fog computing is an emerging network paradigm. Due to its characteristics (e.g., geo-location and constrained resource), fog computing is subject to a broad range of security threats. Intrusion detection system (IDS) is an essential security technology to deal with the security threats in fog computing. We have introduced a fog computing IDS (FC-IDS) framework in our previous work. In this paper, we study the optimal intrusion response strategy in fog computing based on the FC-IDS scheme proposed in our previous work. We postulate the intrusion process in fog computing and describe it with a mathematical model based on differential game theory. According to this model, the optimal response strategy is obtained corresponding to the optimal intrusion strategy. Theoretical analysis and simulation results demonstrate that our security model can effectively stabilize the intrusion frequency of the invaders in fog computing.

Fog computing, as a new paradigm, has many characteristics that are different from cloud computing. Due to the resources being limited, fog nodes/MEC hosts are vulnerable to cyberattacks. Lightweight intrusion detection system (IDS) is a key technique to solve the problem. Because extreme learning machine (ELM) has the characteristics of fast training speed and good generalization ability, we present a new lightweight IDS called sample selected extreme learning machine (SS‐ELM). The reason why we propose “sample selected extreme learning machine” is that fog nodes/MEC hosts do not have the ability to store extremely large amounts of training data sets. Accordingly, they are stored, computed, and sampled by the cloud servers. Then, the selected sample is given to the fog nodes/MEC hosts for training. This design can bring down the training time and increase the detection accuracy. Experimental simulation verifies that SS‐ELM performs well in intrusion detection in terms of accuracy, training time, and the receiver operating characteristic (ROC) value.

Owning to the high processing complexity, the image restoration can only be processed offline and hardly be applied in the real‐time production life. The development of edge computing provides a new solution for real‐time image restoration. It can upload the original image to the edge node to process in real time and then return results to users immediately. However, the processing capacity of the edge node is still limited which requires a lightweight image restoration algorithm. A novel real‐time image restoration algorithm is proposed in edge computing. Firstly, 10 classical functions are used to determine the population size and maximum iteration times of traction fruit fly optimization algorithm (TFOA). Secondly, TFOA is used to optimize the optimal parameters of least squares support vector regression (LSSVR) kernel function, and the error function of image restoration is taken as an adaptive function of TFOA. Thirdly, the LLSVR algorithm is used to restore the image. During the image restoration process, the training process is to establish a mapping relationship between the degraded image and the adjacent pixels of the original image. The relationship is established; the degraded image can be restored by using the mapping relationship. Through the comparison and analysis of experiments, the proposed method can meet the requirements of real‐time image restoration, and the proposed algorithm can speed up the image restoration and improve the image quality.

Modern deep learning enabled artificial neural networks, such as Deep Neural Network (DNN) and Convolutional Neural Network (CNN), have achieved a series of breaking records on a broad spectrum of recognition applications. However, the enormous computation and storage requirements associated with such deep and complex neural network models greatly challenge their implementations on resource-limited platforms. Time-based spiking neural network has recently emerged as a promising solution in Neuromorphic Computing System designs for achieving remarkable computing and power efficiency within a single chip. However, the relevant research activities have been narrowly concentrated on the biological plausibility and theoretical learning approaches, causing inefficient neural processing and impracticable multilayer extension thus significantly limitations on speed and accuracy when handling the realistic cognitive tasks. In this work, a practical multilayer time-based spiking neuromorphic architecture, namely “MT-Spike”, is developed to fill this gap. With the proposed practical time-coding scheme, average delay response model, temporal error backpropagation algorithm and heuristic loss function, “MT-Spike” achieves more efficient neural processing through flexible neural model size reduction while offering very competitive classification accuracy for realistic recognition tasks. Simulation results well validate that the algorithmic power of deep multilayer learning can be seamlessly merged with the efficiency of time-based spiking neuromorphic architecture, demonstrating great potentials of “MT-Spike” in resource and power constrained embedded platforms.