With the rapid development of the Internet of Things (IoT), emerging microservice architectures support scalable and flexible deployment to handle a significant increase in latency-sensitive requests in resource-limited edge. Due to complex data dependencies and instance sharing among microservices, service deployment and request routing tightly coupled, which motivates a complex joint optimization problem. In this case, the difficulty of service orchestration is extremely enlarged when considering multi-instance modeling and fine-grained latency analysis for the strict quality of service (QoS). Furthermore, since the objectives of end-to-end response latency and energy consumption present an inherent conflicting relationship, carefully reconciling the trade-offs between them through efficient microservice orchestration is necessary, but significantly challenging. However, most previous work failed to propose suitable approaches and models to address the above difficulties. Therefore, this paper investigates the energy-efficient microservice orchestration for latency-sensitive applications in edge computing, aiming to minimize both latency and energy consumption. We first develop a multi-instance queuing network model that accurately captures data dependencies and enables detailed analysis of queuing, computing, and communication delays. Then, we propose the Energy-efficient Determination of Microservice Instances (EDMI) algorithm to derive the minimal required number of instances. Furthermore, we design a deep reinforcement learning-based orchestration method, Global-Reward Soft Actor-Critic (GRSAC), which integrates local reward signals into global feedback to mitigate sparse rewards. Finally, we provide theoretical analysis on time complexity and convergence. Experimental results show that our proposed algorithm significantly outperforms existing approaches in reducing both response latency and energy consumption.

The big data era has accelerated the development of artificial intelligence (AI). The Model-as-a-Service (MaaS) paradigm has been used to address the substantial challenges associated with the organization and development of AI services. However, the successful delivery of complete AI applications is contingent upon the robust collaboration between microservice architectures and AI services. In this case, hybrid orchestration of AI services and microservices is highly necessary, but it still brings challenges. Furthermore, due to the heterogeneity of servers, resource competition, and multi-instance, the difficulty of hybrid orchestration modeling is enlarged. When considering intricate service dependencies among AI services and microservices, the tight coupling of deployment and routing leads to complex joint optimization problems, vastly aggravating the pressure of hybrid orchestration. Nonetheless, extant literature largely failed to address the intricate competitive and collaborative relationships between AI services and microservices, and fine-grained latency analysis with multi-instance modeling in hybrid orchestration problem. Therefore, we study joint deployment and routing for hybrid AI services and microservices in heterogeneous edge. Firstly, we conduct a precise analysis of latency and energy consumption, based on queuing networks and multi-instance models. Secondly, we propose a reinforcement learning method based on potential functions and segmented rewards (PS_SAC) to optimize end-to-end latency and system energy consumption, achieving efficient hybrid orchestration. Finally, through extensive simulation experiments, the algorithm demonstrates significant advantages in reducing latency, improving resource utilization, and lowering system energy consumption.

Service meshes built upon ubiquitous microservice architectures, as an emerging paradigm, promise to enhance the flexibility, scalability, and portability of energy-consuming and latency-sensitive applications in edge with limited resources. However, due to intricate microservice dependencies, service multiplexing, and parallel distributed instances, microservice deployment and request routing are highly interdependent. To reduce response latency and energy consumption, such collaborative optimization for efficient service mesh orchestration is necessary, but significantly challenging. Besides, strict service level objective (SLO) requirements and f ine-grained latency analysis with multi-nest routing further impose great difficulties to online orchestration. When considering multi instance modeling and multi-hop data communications for numerous microservices, the difficulty is extremely amplified. Nevertheless, most prevailing work failed to design sophisticate models and methods for addressing the above difficulties, and ignored the inherent transmission energy consumption for highly-concurrent multi-hop data interactions. Therefore, this paper investigates the energy aware service mesh deployment and online request routing in edge. First, we establish a multi-instance queuing network model to accurately analyze the end-to-end response latency with complicated dependencies and multi-hop communications, and optimize energy consumption in a fine-grained manner. Then, to boost the overall performance, we design an efficient multi-dimensional hierarchical deep reinforcement learning algorithm, which enables edges and service instances to cooperate with each other to handle massively concurrent requests. Besides, we propose an energy-aware proactive autoscaling algorithm to carefully adapt to exceedingly dynamic scenarios. Finally, extensive experiments are performed to show our superior performance compared to other baselines.

The rapid development of AI accelerates the implementation and delivery of AI applications in diverse fields. In cloud-edge collaboration, delivering a complete AI application relies on the robust coordination between AI-supporting microservices and AI services. However, most existing studies only coarsely considered monolithic AI service orchestration while neglecting microservice orchestration. Such coarse-grained orchestration severely impacts application performance. To enable diverse high-performance AI applications, fine-grained hybrid orchestration of AI services and microservices (HOAIM) is highly desirable, yet presents formidable challenges. Due to heterogeneous services, call dependencies, and service multiplexing, fine-grained hybrid orchestration modeling is highly non-trivial. Moreover, the tight coupling between deployment and routing results in a complex joint optimization problem. To address this, we first propose a heterogeneous service orchestration network that supports orchestration optimization and automated management. Then, based on queuing networks and multi-instance models, we conduct an accurate analysis of delay and load. Furthermore, to achieve efficient hybrid orchestration, we propose preference-driven resource allocation and instance computation algorithms, along with reinforcement learning with action masking and reward shaping. Finally, extensive trace-driven simulations demonstrate that our algorithms optimize average response delay by up to 41.83%, and achieve significant advantages in load balancing, response success rate, and resource efficiency.

With the rapid advancement of edge computing, service mesh has emerged as a critical technology for improving network performance, owing to its flexibility and scalability. However, massive online applications in edge clouds pose significant challenges to microservice orchestration, including high concurrency, complex service dependencies, strict response delay requirements, and fast orchestration needs. Addressing these challenges requires efficient and fast orchestration strategies, but existing approaches often lack accurate models and effective algorithms to handle these complexities. To tackle the above challenges, this paper proposes an efficient Symmetric Microservice Deployment (SMD) algorithm for fast orchestration. First, accurate modeling is achieved with the queuing network, which analyzes intertwined requests and calculates detailed delays. Moreover, the SMD algorithm simplifies the coupling between deployment and routing by considering internal dependencies during deployment. This integrated approach eliminates the need for separate routing solutions and ensures provable optimal performance under symmetric deployment. Experimental results demonstrate that, compared to four baseline algorithms, the proposed method reduces response delay by 25.5% and execution time by 58.4%, showcasing the potential and advantages of the algorithm for optimizing microservice orchestration in edge clouds networks.

Low Earth Orbit (LEO) satellite networks, with their low latency, high bandwidth, and global coverage, are becoming key technologies for applications like real-time video transmission. As satellite networks expand, effectively managing multicast traffic and optimizing bandwidth utilization have become major challenges for efficient video distribution. Although Software-Defined Multicast (SDM) technology has made progress in bandwidth optimization, existing SDM methods are still focused on constructing Steiner trees, making it difficult to address the dynamic changes and high-load issues in LEO satellite networks. This paper frames the multicast tree construction problem as a Joint Path Optimization Game (JPOG). We propose a Cooperative Game-Theoretic Routing (CGMR) Algorithm based on game theory, which optimizes multicast path selection and achieves load balancing by introducing a link cost-sharing mechanism. Additionally, we propose a two-stage A* path generation algorithm to improve path search efficiency. Theoretically, this paper proves that JPOG is a potential game and can converge to a pure strategy Nash equilibrium (PSNE) within a finite number of iterations. The results showed that JPOG outperformed other algorithms, achieving lower link load, path cost, and superior load balancing, demonstrating its effectiveness in optimizing multicast routing and resource management in large-scale LEO satellite networks.

The rapid development of service computing has led to the emergence of scalable and flexible architectures such as microservices and Artificial Intelligence as a Service (AaaS), enabling the orchestration of AI-driven intelligent applications. However, existing work on intelligent applications orchestration overlooked essential microservice components that support AI services, resulting in coarse-grained and incomplete models. To ensure system integrity and enhance QoS, fine-grained collaborative orchestration of microservices and AI services is crucial. However, this poses significant challenges due to complex service dependencies, high request concurrency, and heterogeneous resource demands in edge environments. Moreover, the strong coupling between service deployment and request routing complicates their joint optimization, since effective decisions in one depend on the other. To address these challenges, we propose a collaborative orchestration framework that jointly optimizes the deployment of microservices and AI services along with probabilistic request routing in edge environments. We formulate the problem as a mixed-integer nonlinear program and leverage Jackson queuing networks for accurate delay modeling. To solve this, we develop a dual time scale hybrid greedy proximal policy optimization (DTS-HGPPO) algorithm that performs instance-level deployment and adaptive routing, enhanced with iterative instance planning, action masking and intrinsic motivation mechanisms. Extensive trace-driven experiments demonstrate that our method significantly reduces both response delay and service cost compared to state-of-the-art baselines.

Microservice as a promising architecture has been widely employed in edge computing to support sensitive-latency online applications. Unfortunately, the deployment of numerous microservices creates complex invocations and requires frequent communications, which brings significant challenges to service deployment and request routing. Moreover, the strict requirements for low energy consumption and low latency in edge computing further exacerbate these difficulties. In this case, it is crucial to optimize the joint microservices deployment and request routing using a meticulous and energy-efficient approach. However, existing studies often overlook their interdependence and treat them as separate problems. Therefore, we propose a fine-grained approach in this paper to jointly optimize the deployment and request routing of microservices within edge computing scenarios. First, we utilize queuing networks to conduct detailed modeling and mathematical analysis that study the complex invocation relationships, microservice instance sharing, and communication latency. Second, we propose an energy-efficient microservice orchestration algorithm, referred to as Cluster-Processing-based Adaptive Memory Procedure. This algorithm maintains a memory storing elite solution elements, and it iteratively picks up suitable elements from the memory to construct superior solutions. Finally, extensive simulation experiments demonstrate that the proposed algorithm outperforms baseline algorithms significantly in terms of response latency and energy consumption.

Machine unlearning aims to remove the information of specific data from a trained machine learning model while retaining its utility for the remaining data, so as to meet the requirements of privacy regulations. Existing unlearning methods often assume a balanced data distribution, but neglect the real-world, long-tailed scenarios, where the decision boundaries of tail classes are frequently distorted due to insufficient sample representation, thereby reducing the unlearning efficacy. In this paper, we propose the first Long-Tailed Machine Unlearning (LTMU) framework from a unified decision-boundary perspective. Our framework begins with a directional boundary repair scheme designed to enrich the distorted decision boundary of the tail class, and then develop a novel boundary retraction approach tailored for long-tailed unlearning, dispersing both the augmented and original features throughout the feature space. This bidirectional manipulation not only offers a unified interpretation of the relationship between long-tailed learning and unlearning, but also enables flexible control over both repair and unlearning processes through the generation of augmented features, thereby effectively accomplishing the long-tailed unlearning task. Extensive experiments across multiple datasets and neural network architectures demonstrate the effectiveness of our framework in achieving complete unlearning of tail classes in long-tailed distributions.

The rapid proliferation of Internet of Things (IoT) devices has increased the variety of devices and data traffic, making data management and analysis more complex. This complexity has raised the demand for efficient device identification methods to ensure the smooth operation of the network. Conventional identification methods rely on Machine Learning (ML) and Deep Learning (DL), which either suffer from unstable feature engineering or rely on large labeled datasets with confined representation. To overcome these shortcomings, generic hybrid representations of raw traffic are essential for precise device identification. Additionally, existing work mainly investigated device identification in clouds, incurring high network latency and computation costs. A few studies have identified IoT devices in edge, but such methods used simple neural networks, resulting in incomplete representation and redundant operations. Comprehensive representations typically require complex models, but the limited resources at the edge are insufficient to execute these models. Therefore, this paper proposes a lightweight hybrid device identification (LHDI) approach, which achieves efficient device identification in resource-constrained edge nodes. First, we adopt the unsupervised pre-training to enhance the characterization of network packets. Second, we devise LHDI by integrating bidirectional long short-term memory (Bi-LSTM) and Transformerbased blocks in a parallel configuration. Third, a pruning framework is introduced to automatically reduce Transformer parameters using structured sparsity methods without retraining. By reducing redundant neural network parameters, the proposed lightweight model facilitates effective device identification in edge, without losing representation capabilities. Experimental results demonstrate that our methods deliver high accuracy with low cost compared to others.

The integration of microservice architecture and edge computing offers innovative solutions for highly interactive, low-latency Internet applications. To manage the dynamic nature of requests in edge computing, microservice autoscaling techniques are frequently employed. However, the resource limitation of individual edge servers and the heterogeneity among edge servers present significant challenges for autoscaling in edge computing. Meanwhile, few studies have considered the long-term optimization and the joint optimization of instance adjustment and request routing in edge computing. This paper aims to fill these gaps. First, we propose Global Horizontal Pod Autoscaler (GHPA), a novel framework that addresses microservice autoscaling from the perspective of edge server clusters. Second, we consider the joint optimization of instance adjustment and request routing, and formulate a long-term optimization problem. Third, we transform the long-term optimization problem into a Markov Decision Problem (MDP) and use reinforcement learning techniques to solve it. Finally, we conduct extensive experiments using both real and synthetic data. The experiment results demonstrate that our algorithm achieves at least a 10% performance improvement in various test environments compared to state-of-the-art algorithms.

The deployment of the microservice architecture in edge networks presents new opportunities for supporting latency-sensitive network services. However, most such services are both computation-intensive and energy-consuming, posing significant challenges for edge nodes with constrained computing resources and energy supply. Therefore, designing efficient microservice orchestration strategies to reduce service latency and network energy consumption is essential but highly challenging. Due to frequent communication among microservices, service deployment and request routing are tightly coupled, which lead to a complex joint optimization problem. This complexity further increases when considering large-scale microservices under multi-instance modeling and fine-grained analysis. Nevertheless, previous work has failed to address these challenges and largely overlooked the balance between latency and energy consumption. To overcome these issues, this paper proposes an energy-latency balanced microservice orchestration method to jointly minimize service latency and energy usage. First, we adopt multi-instance modeling to enable precise end-to-end latency analysis, and integrate an energy model to quantify overall network consumption. Then, we design the Node Ranking Matrix-based Microservice Orchestration Algorithm (NRMA), which dynamically selects high-ranking nodes based on centrality and energy metrics, thereby balancing latency and energy in the deployment stage. Moreover, we use the proportional routing strategy that distributes user request traffic according to the number of deployed instances, preventing node overload and reducing cross-node communication. Experimental results show that the proposed method is significantly better than the baseline algorithms in terms of latency and energy consumption, and achieves significant results.

The emerging microservice architecture offers opportunities for accommodating delay-sensitive applications in edge. However, such applications are computation-intensive and energy-consuming, imposing great difficulties to edge servers with limited computing resources, energy supply, and cooling capabilities. To reduce delay and energy consumption in edge, efficient microservice orchestration is necessary, but significantly challenging. Due to frequent communications among multiple microservices, service deployment and request routing are tightly-coupled, which motivates a complex joint optimization problem. When considering multi-instance modeling and fine-grained orchestration for massive microservices, the difficulty is extremely enlarged. Nevertheless, previous work failed to address the above difficulties. Also, they neglected to balance delay and energy, especially lacking dynamic energy-saving abilities. Therefore, this paper minimizes energy and delay by jointly optimizing microservice deployment and request routing via multi-instance modeling, fine-grained orchestration, and dynamic adaptation. Our queuing network model enables accurate end-to-end time analysis covering queuing, computing, and communicating delays. We then propose a delay-aware reinforcement learning algorithm, which derives the static service deployment and routing decisions. Moreover, we design an energy-aware dynamic frequency scaling algorithm, which saves energy with fluctuating request patterns. Experiment results demonstrate that our approaches significantly outperform baseline algorithms in both delay and energy consumption.

The service modules of the traditional Mobile Edge Computing (MEC) are difficult to deploy, extend, and maintain in real networks because of the highly sophisticated systems. To promote the generalization, openness, and flexibility of the network edge environment, an increasing number of studies are exploring the integration of microservices with MEC. However, the existing work usually treats microservice deployment and request routing as two separate issues, ignoring the interaction between them. Therefore, this paper focuses on the joint optimization of microservice deployment and request routing in the multi-edge cloud scenarios. We establish a problem model for minimizing the average response latency, considering the transmission of requests across edge clouds. Then, in view of the complexity of the scene, this paper proposes a joint training strategy of microservice deployment and request routing based on deep reinforcement learning and Best Fit Decreasing algorithm. The algorithm takes the change of microservice deployment scheme as the action of the agent, introduces the Best Fit Decreasing algorithm to construct request routing based on the deployment scheme, and calculates rewards using the complete joint microservice deployment and request routing scheme for subsequent network training. Finally, experimental results show that the proposed algorithm can effectively reduce the response time delay and system running power compared with other algorithms.

Lightweight microservices as a software architecture have been widely adopted in online application development. However, in highly-concurrent microservice scenarios, frequent data communications, complex call dependencies, and dynamic delay requirements bring great challenges to efficient microservice orchestration. In this case, service deployment and request routing are interactively-coupled in multi-instance modeling, and cannot be locally optimized effectively, thereby enlarging the difficulty for collaborative orchestration. To accommodate time-varying request properties and dynamic microservice multiplexing, orchestration schemes are frequently adapted to real-time parallel request queues, further complicating the difficulty. Nevertheless, most previous work failed to propose appropriate models and methods for the above issues. Therefore, this paper investigates the online microservice orchestration with probabilistic routing for dynamic call graphs in clouds. First, we formulate the time-slot-based joint optimization problem as a Markov Decision Process. The open Jackson queuing networks are used to accurately establish multi-instance models and analyze the request queuing, processing, and communicating delays. Then, we propose an efficient curiosity-driven deep reinforcement learning algorithm, which meticulously implements instance-level orchestration through multi-dimensional collaborative decisions and multi-time-scale trigger events. Finally, through comprehensive trace-driven experiments, our proposed approach significantly outperforms other baselines in terms of orchestration cost and resource utilization.

Service mesh architectures are emerging as a promising microservice paradigm for developing online cloud applications. However, in large-scale microservice scenarios, frequent service communications, intricate call dependencies, and stringent latency requirements bring great pressure to efficient service mesh orchestration. In this case, the problems of service deployment and request routing based on service mesh architectures are tightly-coupled and interdependent, and cannot be effectively optimized individually, enlarging the difficulty for collaborative orchestration. When microservice multiplexing, parallel dependencies, and multi-instance modeling are considered, the difficulty is further aggravated. Nonetheless, most existing work failed to propose appropriate models and methods for the above challenges. Therefore, this article studies the large-scale service mesh orchestration with probabilistic routing and constrained bandwidths for parallel call graphs. We leverage the open Jackson queuing network theory to capture crucial microservices and analyze request processing, queuing, and communication latency for massive user requests in a fine-grained way. Then, this article proposes an efficient three-stage heuristic, which achieves elegant multi-instance consolidation and probabilistic multi-queue routing to reduce response latency and cost. We also provide the algorithm complexity and mathematical analysis of the performance. Finally, extensive trace-driven experiments are performed to validate the superiority of our proposed algorithm over other baselines.

The rapid development of satellite communication technologies has significantly enhanced global connectivity, with Low Earth Orbit (LEO) satellite networks playing a crucial role. However, the high-speed movement of LEO satellites introduces dynamic and unstable network topologies, presenting challenges in routing and traffic engineering. Traditional routing algorithms, such as Dijkstra’s, often struggle to adapt to these dynamic conditions, leading to inefficiencies in load balancing and resource utilization. In response, this paper proposes an Iterative Region-Based Probabilistic Forwarding (IRPF) strategy within a Software-Defined Satellite Networking (SDSN) framework. Our strategy dynamically assigns forwarding probabilities to satellite ports based on link traffic weights, optimizing routing paths through a feedback iteration process. To prevent the algorithm from converging to local optima, we introduce a local adjustment mechanism that fine-tunes forwarding probabilities. The experimental results show that when the scale of the satellite network is relatively small, the IRPF strategy incurs lower total link traffic costs compared to the Dijkstra algorithm. Additionally, it improves the Gini coefficient and packet loss rate by approximately 20% and 30%, respectively. These results demonstrate the effectiveness and stability of this method in routing and traffic engineering.

Given the increased complexity and volume of IP traffic, maintaining efficient and secure network operations poses substantial challenges. IPSec gateways, critical for ensuring secure communications over IP networks, require robust and efficient security policy search mechanisms. Traditional methods, such as the interval tree algorithm, often fall short in terms of speed and scalability when faced with large and dynamic IP ranges. This paper addresses these demands by proposing a novel IP range search algorithm termed Fast Limit Hash Interval-Tree Search (FLHIS). The FLHIS algorithm utilizes a two-stage processing approach for IP ranges within security policies, combining the range matching capabilities of interval trees with the rapid matching abilities of hash tables to achieve swift target security policy searches. Additionally, a limiting value is set to control the data volume within each hash node, balancing the data scale between nodes and minimizing the search time within nodes. Experimental comparisons with traditional interval tree algorithms demonstrate that the FLHIS algorithm significantly improves performance, reducing search times to just 12.5% of those observed with the interval tree algorithm in the best-case scenario. This advancement is crucial for enhancing the performance and reliability of IPSec gateways in contemporary network environments.

Pattern matching algorithms are widely used in fields such as traffic classification and management, user behavior analysis, and more. The increasingly large and complex network traffic poses significant challenges to feature matching processes. The cuckoo filter, capable of quickly determining whether an element is in a set, can be combined with pattern matching algorithms to accelerate feature matching. Building upon previous research, we propose an improved Wu-Manber (WM) algorithm that further reduces the size of the hash table generated during preprocessing, decreases the number of hash computations, and incorporates a cuckoo filter to eliminate unmatched text prefixes. This improved WM algorithm considers factors affecting algorithm performance, such as the large scale of the pattern set and the prevalence of repeated pattern string suffixes. Experimental results demonstrate that our proposed algorithm, Fast Parallel Wu-Manber (FSPRWM), significantly enhances matching speed while effectively reducing memory consumption.

In recent years, deep neural networks (DNNs) have witnessed extensive applications, and protecting their intellectual property (IP) is thus crucial. As a non-invasive way for model IP protection, model fingerprinting has become popular. However, existing single-point based fingerprinting methods are highly sensitive to the changes in the decision boundary, and may suffer from the misjudgment of the resemblance of sparse fingerprinting, yielding high false positives of innocent models. In this paper, we propose ADV-TRA, a more robust fingerprinting scheme that utilizes adversarial trajectories to verify the ownership of DNN models. Benefited from the intrinsic progressively adversarial level, the trajectory is capable of tolerating greater degree of alteration in decision boundaries. We further design novel schemes to generate a surface trajectory that involves a series of fixed-length trajectories with dynamically adjusted step sizes. Such a design enables a more unique and reliable fingerprinting with relatively low querying costs. Experiments on three datasets against four types of removal attacks show that ADV-TRA exhibits superior performance in distinguishing between infringing and innocent models, outperforming the state-of-the-art comparisons.

Recently, blockchain is introduced to ensure the security of the device data in Internet of Things (IoT) systems. However, storing the entire blockchain ledger in resource-constrained IoT devices is impractical. A few existing papers attempt to mitigate the storage issues of the blockchain ledgers through the collaborative storage. Nonetheless, these studies solely consider collaborative storing of the entire blockchain ledger in a single consensus unit, treating all the nodes as an individual peer but ignoring which nodes should be assigned to form a consensus unit together. This may lead to significant latency in block invocations among the nodes. To this end, this article innovatively explores the grouping of all the devices in the IoT network into multipeers at a global level which significantly reduces the access latency. In this article, we propose a clustering-based collaborative storage scheme for the blockchain in storage-limited IoT systems. The proposed algorithm takes storage and communication latency into consideration and clusters various IoT nodes into multiple peers, ensuring that the entire blockchain stays updated within these clusters. Furthermore, we propose a series of effective block allocation and replacement strategies in both the static and dynamic scenarios. The experimental results verify that our algorithm effectively solves the problem of insufficient storage in blockchain systems.

In large smart factories, massive microservices compose complicated modular IT systems, providing various service functions. However, large microservices-based IT systems incur sophisticated communications and invocations among the massive microservices, which calls for efficient orchestration techniques to meet the high requirements in smart factories. Also, complex data interdependencies among microservices tightly couple deployment with routing, further intensifying the difficulties in orchestration. Such challenges demand delicate joint optimization of service deployment and request routing, which however, are neglected by previous work. In this case, this article investigates the collaborative optimization of microservice deployment and routing in smart factories. First, we construct a communication queuing network model to analyze service performance under dynamic load. Second, two heuristics are proposed to provide differentiated deployment and routing schemes for various demands. Finally, rigorous experiments validate that our approach significantly enhances network efficiency across various production scenarios in smart factories.

The emerging low earth orbit (LEO) broadband satellite networks are creating new opportunities to enable superior video distribution. With numerous satellites deployed, broadband constellations are capable of distributing videos across the globe by efficient multicasting techniques. However, existing work only studied IP multicast for broadband constellations, which suffer from limited scalability and tree performance. With recent breakthroughs in software defined networking, novel software defined multicasting (SDM) techniques manage to achieve efficient data transfer through intelligent and granular management, outperforming traditional IP Multicast. This paper leverages software defined multicasting in the promising broadband constellations to empower satellite-based Internet video distribution. Based on rectilinear Steiner trees, this paper proposes a novel software defined multicasting framework for broadband satellite networks. In addition, this paper designs simple, agile, and scalable multicast segment routing protocols implementing source routing and equal cost multipath routing. The proposed protocols also adapt to frequent member updates and network failures with efficient tree recovery and local rerouting mechanisms. Comprehensive experiments demonstrate the effectiveness and efficiency of our approach when compared with traditional algorithms.

Point-of-interest (POI) recommendation has drawn much attention with the widespread popularity of location-based social networks (LBSNs). Previous works define long- and short-term trajectories via long short-term memory (LSTM) to capture user's stable and current preference, and incorporate context factors to improve recommendation effectiveness. However, these factors have different impacts on POI recommendation, and meanwhile, they are mutually influenced. Existing studies either model all the factors separately, or feed them into the same LSTM model, which are less meticulous for modeling the LBSNs trajectories. To address such issues, we revisit the long- and short-term preference learning for next POI recommendation by presenting a novel framework that can model both POI level and semantic level check-in trajectories. We develop a hierarchical LSTM to learn the two-level representations and consider the interplay of the two-level features by adding factors to the gates of LSTMs for each trajectory. We further construct a semantic filter to improve the recommendation efficacy. Experimental results using two real-world check-in datasets indicate that the proposed framework outperforms four state-of-the-art baselines regarding two commonly used metrics.

Edge computing technologies with container-based microservice architectures promise to provide stable and low-latency services for large-scale and complex edge applications. However, due to the limited CPU and storage resources in edge computing scenarios, the coarse-grained service deployment on edge nodes causes performance bottlenecks. In addition, the effective deployment of microservices is tightly correlated with request routing, but the current research ignores the joint optimization of multi-instance deployment and routing. In this paper, we first model the problem of jointly optimizing service deployment and routing in a dynamically changing environment with multi-edge network collaboration based on a queuing network analysis. Secondly, we design heuristic algorithms to scale microservice instances horizontally in dynamic user request states. In addition, we propose a reinforcement learning algorithm based on reward shaping (RSPPO) to minimize user waiting delay and edge network resource consumption. We also solve the microservice deployment and request routing problem for multi-edge collaboration to achieve load balancing among edge nodes. Finally, extensive experiments verify the significant and extensive effectiveness of our algorithm.

Microservices as an emerging architecture are creating new opportunities to enable superior network services in Mobile Edge Computing (MEC). In the presence of huge amounts of user requests, the massive communications among microservices have become notoriously complicated. Due to the intricate data dependencies of the microservices, the overall performance of large-scale MEC applications simultaneously depends on both service deployment and request routing. However, most existing work ignores the interdependencies of microservices and studies the deployment and routing as two isolated problems. In this case, this paper investigates the joint optimization of service deployment and request routing in edge computing. We first formulate a delay minimization problem via mixed integer linear programming and queuing analysis, and then provide a hardness proof on the problem. In addition, this paper presents a 2-approximation algorithm, followed with rigorous mathematical proofs to demonstrate the approximation ratio. The proposed two-phase algorithm consists of rounding based service deployment and adaptive-scaling-based request routing policies, which employ fine grained joint optimization to minimize service response delay. Finally, we illustrate the near-optimal performance of the proposed algorithm via comprehensive experiments.

The practical needs of the “right to be forgotten” and poisoned data removal call for efficient machine unlearning techniques, which enable machine learning models to unlearn, or to forget a fraction of training data and its lineage. Recent studies on machine unlearning for deep neural networks (DNNs) attempt to destroy the influence of the forgetting data by scrubbing the model parameters. However, it is prohibitively expensive due to the large dimension of the parameter space. In this paper, we refocus our attention from the parameter space to the decision space of the DNN model, and propose Boundary Unlearning, a rapid yet effective way to unlearn an entire class from a trained DNN model. The key idea is to shift the decision boundary of the original DNN model to imitate the decision behavior of the model retrained from scratch. We develop two novel boundary shift methods, namely Boundary Shrink and Boundary Expanding, both of which can rapidly achieve the utility and privacy guarantees. We extensively evaluate Boundary Unlearning on CIFAR-10 and Vggface2 datasets, and the results show that Boundary Unlearning can effectively forget the forgetting class on image classification and face recognition tasks, with an expected speed-up of 17x and 19x, respectively, compared with retraining from the scratch.

Machine learning (ML) has achieved huge success in recent years, but is also vulnerable to various attacks. In this article, we concentrate on membership inference attacks and propose Aster, which merely requires the target model's black-box API and a data sample to determine whether this sample was used to train the given ML model or not. The key idea of Aster is that the training data of a fully trained ML model usually has lower prediction sensitivities compared with that of the non-training data (i.e., testing data). Less sensitivity means that when perturbing a training sample's feature value in the corresponding feature space, the prediction of the perturbed sample obtained from the target model tends to be consistent with the original prediction. In this article, we quantify the prediction sensitivity with the Jacobian matrix which could reflect the relationship between each feature's perturbation and the corresponding prediction's change. Then we regard the samples with a lower as training data. Aster can breach the membership privacy of the target model's training data with no prior knowledge about the target model or its training data. The experiment results on four datasets show that our method outperforms three state-of-the-art inference attacks.

Demand forecasting (DF) plays an essential role in supply chain management, as it provides an estimate of the goods that customers are expected to purchase in the foreseeable future. While machine learning techniques are widely used for building DF models, they also become more susceptible to data poisoning attacks. In this article, we study the vulnerability of targeted poisoning attacks for linear regression DF models, where the attacker controls the behavior of forecasting models on a specific target sample without compromising the overall forecasting performance. We devise a gradient-optimization framework for targeted regression poisoning in white-box settings, and further design a regression value manipulation strategy for targeted poisoning in black-box settings. We also discuss some possible countermeasures to defend against our attacks. Extensive experiments are conducted on two real-world datasets with four linear regression models. The results demonstrate that our attacks are very effective, and can achieve a high prediction deviation with control of less than 1% of the training samples.

Driven by the large amount of spatio-temporal data obtained from location-based social networks, the implementation of cross-domain user linkage, also known as the User Identity Linkage (UIL), has attracted increasing research attentions. While most of the existing UIL works discretize the spatio-temporal sparse data when identifying encountering or co-located events for UIL, user’s distinctive behavior patterns implicit in the “check-in” spatio-temporal data with continuous nature pave the way for enhancing UIL performance. In this paper, we propose an approach dubbedCP-Linkthat exploits user behavior patterns in a continuous way. In CP-Link, the continuous space is divided into irregularly shaped stay regions, and a continuous time-based improved dynamic time warping (IDTW) method is proposed to calculate the similarity. To bridge the gap between the ideal scenario with ample records and the reality with sparse data, we adopt the user-associated location frequent pattern (LFP) model to compensate for the sparse deficiency. Extensive experiments conducted on real-world datasets demonstrate the effectiveness and superiority of CP-Link, which outperforms the state of the arts by more than 20% in terms of the AUC.

Microservices are an architectural and organizational paradigm for Internet application development. In cloud data centers, delay-sensitive applications receive massive user requests, which are fed into multiple queues and subsequently served by multiple microservice instances. Accordingly, effective deployment of multiple queues and containers can significantly reduce queuing delay, processing delay, and communication delay. Due to the increased complexity of call dependencies and probabilistic routing paths, the deployment of service instances fully interacts with request routing, bringing great difficulties to service orchestration. In this case, it is valuable to simultaneously consider service deployment and request routing in a fine-grained manner. However, most existing studies considered them as two independent components with local optimization, while data dependencies and the instance-level deployment are ignored. Therefore, this paper proposes to jointly optimize the deployment and request routing of microservice call graphs based on fine-grained queuing network analysis and container orchestration. We first formulate the problem as a mixed-integer nonlinear program and exploit open Jackson queuing networks to model intrinsic data dependencies and analyze response latency. To optimize the overall cost and latency, this paper presents an efficient two-stage heuristic algorithm, which consists of a resource-splitting-based deployment approach and a partition-mapping-based routing method. Further, this paper also provides mathematical analysis on the performance and complexity of the proposed algorithm. Finally, comprehensive trace-driven experiments demonstrate that the overall performance of our approach is better than existing microservice benchmarks. The average deployment cost is reduced by 27.4% and end-to-end response latency is reduced by 15.1% on average.

Point-of-interest (POI) recommendation service has drawn growing attention with the widespread popularity of location- based social networks (LBSNs). Recent research methods on POI recommendation based on graph embedding have mainly focused on explicit interactions of LBSN objects such as user's check-ins on POIs and social relationships, while neglecting implicit relationship that cannot be directly observed but may notably contribute to the POI recommendation. This paper presents VirHpoi, a heterogeneous hypergraph embedding method for POI recommendation in LBSNs with three original contributions. First, we model the LBSNs as a hypergraph to capture the complex interactions in LBSNs and learn the hypergraph by preserving homophily and interaction attribute affinity of the LBSNs. Second, we introduce the notion of “virtual hyperedges” to capture the intrinsic correlations of POIs. Virtual hyperedges incorporate implicit yet informative connections of the check-in patterns in LBSNs in terms of geographical and semantic characteristics. Third, we propose techniques to learn heterogenous hypergraph embedding on the complex LBSN graph with both homogenous edges and heterogenous hyperedges with dual objectives: we aim to preserve the homophily of objects intra domain by maximizing the co-occurrence probability of all homogenous edges, and we want to learn the interaction attribute affinity across domains by maximizing the probability of predicting the target object in the hyperedges. As a result, our approach can preserve both the intra domain homophily of objects and the interaction attribute affinity across domains by learning low-dimensional embeddings of LBSN objects and then make more effective recommendations based on the embeddings. Extensive experiments on four real-world datasets show the effectiveness and superiority of VirHpoi compared with the state-of-the-art methods.

Computer vision-based license plate recognition (LPR) has been widely deployed for automatic vehicle identity inspection due to the offered convenience and efficiency. However, the practical LPR systems are potentially vulnerable to malicious attacks, which may lead to incorrect recognition and impact the safety of transportation. Previous studies of attacking strategies targeting LPR systems mainly focused on evasion attacks, which are less efficient than model poisoning attacks that can cause mis-classification through directly manipulating the parameters of the victim model other than perturbing each testing sample. To fill this gap, we conduct the first systematic study on the vulnerability of LPR systems against model poisoning attacks. In specific, we aim to compromise the integrity of the model training such that the attacked LPR system would mis-classify all the samples from the victim class to the attacker-chosen class. To achieve this, we fine-tune the feature extractor layers of the LPR model such that it can obtain similar feature representations given samples belong to victim and attacker-chosen classes. This is implemented in a generator-discriminator fashion, where a discriminator learns to classify the victim and attacker-chosen classes given the input samples. Subsequently, the feature extractor is fine-tuned to generate manipulated features that can confuse the discriminator. Our empirical results on the CCPD dataset demonstrate that the proposed attacking strategy can substantially compromise LPR systems with high success rates.

The emerging low earth orbit (LEO) satellite networks are expected to provide the world’s most advanced Internet services. Besides, terrestrial networks are in constant evolution and already moving to embrace the relatively new paradigm of software defined networking (SDN). In this paper, we take the advantages of SDN features and leverage traffic engineering (TE) to enhance the ISL performance in broadband LEO satellite networks. We investigate unicast and multicast TE for SDN-enhanced LEO constellations to empower satellite-based Internet services. In LEO satellite networks, unicast supports ubiquitous network access and provides basic network services, while multicast features superior satellite-based video distribution. For unicast TE in grid ISL networks, we present a simple yet efficient${k}$-segment routing based strategy with segment routing (SR) techniques, which can achieve near optimal max link utilization when compared with the multi-commodity flow solution. In the meanwhile, our solution eliminates routing tables and only imposes little routing information stored in packet headers. For multicast TE, we employ rectilinear Steiner trees (RSTs) to maximize bandwidth saving and exploit obstacle-avoiding rectilinear Steiner trees (OARSTs) to address the contention of multiple multicast groups. Based on RSTs and OARSTs, we propose an effective per-flow management scheme to balance traffic among multiple multicast flows in the presence of limited link capacities. Simulation results demonstrate the effectiveness and efficiency of our approaches on reducing routing information and accommodating more multicast groups.

With the development of location-based services (LBS), concerns on location privacy frequently arise. Location data often contains users' sensitive information, and direct release it may pose a threat to users' privacy. Differential privacy (DP), as a privacy preserving method with solid mathematical foundation, has been widely used in location data release. However, most if not all of the existing location DP mechanisms only consider static scenarios or perturb the location at single timestamp, which are vulnerable to the so-called location-dependent attacks (LDA) in continuous LBS queries. In this paper, an optimal location DP mechanism against LDA is proposed. Firstly, the necessary conditions for LDA defense are derived by combining the perturbation mechanism of location DP. Then the algorithm of safe perturbance region generation is established to dynamically calculate the perturbation range at each timestamp. Finally, we set up the optimization problem with the real-time quality loss as the optimization objective and the location DP and safe perturbance region as the optimization conditions, and realize the optimal DP mechanism for LDA by solving the optimization problem. Experiment results on real-world datasets show that our mechanism can effectively resist LDA, which also balance privacy protection and data utility well.

Smart contracts, one of the success stories in blockchain 2.0, have been widely utilized in a broad range of applications, including those involving Internet of Things (IoT). Given the fast-pace nature of the topic, it can be challenging for the research community to keep track of the latest advances. Hence, in this article, we perform a comprehensive, in-depth review of known security challenges (e.g., inherently vulnerable particularities, programming vulnerabilities, and attacks) and potential research opportunities associated with the deploying of smart contracts in an IoT setting. We hope this survey will serve as a starting point for the readers seeking to understand and explore the potential applications of smart contracts.

The emerging of machine learning has massively promoted the abilities of computational sustainability in natural resource management and allocation. Many Internet giants such as Google, Amazon, and Microsoft now provide Machine Learning as a Service (MLaaS) to meet the increasing demand for machine learning services. However, the prediction results of training data and testing data with the same machine learning model in MLaaS have remarkable differences, and thus the attackers can leverage machine learning techniques to launch the so-called membership inference attacks, i.e., to infer whether a record is in the training data or not. In this paper, we propose MIASec that can guarantee the data indistinguishability of the training data and thereby has the ability to defend against membership inference attacks in MLaaS. The key idea of MIASec is to narrow the dynamic ranges of vital features in the training data, such that the training data, the testing data, and even the synthetic data have almost semblable prediction results by the same machine learning model. With elaborated design on modifying the values of vital features in the training data, MIASec can thus reduce the differences between the model's outcomes of training data and testing data, thereby protecting the training data in effect while keeping the model's accuracy stable. We empirically evaluate MIASec on machine learning models trained by off-line neural networks and on-line MLaaS. Using realistic data and classification tasks, our experiment results show that MIASec can defend the membership inference attacks effectively. In particular, MIASec can reduce the precision and recall of attacks respectively by 11.7 and 15.4 percent in average, and by 18.6 and 21.8 percent at best.

The enabling Internet-of-Things technology has inspired many innovative sensing mechanisms by repurposing the onboard sensors. Leveraging the built-in acoustic sensors for ranging is among one of the interesting applications. However, among the few studies on acoustic ranging, the one-way sensing method suffers from synchronization errors and requires cumbersome kernel modifications; the other two-way approaches overcome these shortcomings, but they are sensitive to system delays. In this case, this paper proposes a novel lightweight one-way sensing paradigm without the above drawbacks. The key insight of this paper is to perform ranging by estimating the propagation time of acoustic signals via linear frequency modulation signal mixing. Such a signal mix operation can translate range estimation into fine-grain frequency estimation, thereby enhancing ranging accuracy. In addition, our system can have multiple receivers co-exist and thus the measurement dimensions are boosted. We have implemented and evaluated our system prototype in real-world settings. The prototype demonstrated centimeter-level ranging performance.

In recent decades, unmanned aerial vehicles (UAVs, also known as drones) equipped with multiple sensors have been widely utilized in various applications. Nevertheless, constrained by limited battery capacities, the hovering time of UAVs is quite limited, prohibiting them from serving a wide area. To cater with remote sensing applications, people often employ vehicles to transport, launch, and recycle them. The so-called vehicle-drone cooperation (VDC) benefits from both the far driving distance of vehicles and the high mobility of UAVs. Efficient routing and scheduling can greatly reduce time consumption and financial expenses incurred in VDC. However, previous works in vehicle-drone cooperative sensing considered only one drone, thus unable to simultaneously cover multiple targets distributed in an area. Using multiple drones to sense different targets in parallel can significantly promote efficiency and expand service areas. Therefore, we propose a novel problem, referred to as vehicle-assisted multidrone routing and scheduling problem. To tackle the problem, we contribute an efficient algorithm, referred to as vehicle-assisted multi-UAV routing and scheduling algorithm (VURA). In VURA, we maintain and iteratively update a memory containing candidate UAV routes. VURA works by iteratively deriving solutions based on UAV routes picked from the memory. In every iteration, VURA jointly optimizes anchor point selection, path planning, and tour assignment via nested optimization operations. To the best of our knowledge, we are the first to tackle this novel yet challenging problem. Finally, performance evaluation is presented to demonstrate the effectiveness and efficiency of our algorithm when compared with existing solutions.

Social media networks have shown rapid growth in the past, and massive social data are generated which can reveal behavior or emotion propensities of users. Numerous social researchers leverage machine learning technology to build social media analytic models which can detect the abnormal behaviors or mental illnesses from the social media data effectively. Although the researchers only public the prediction interfaces of the machine learning models, in general, these interfaces may leak information about the individual data records on which the models were trained. Knowing a certain user's social media record was used to train a model can breach user privacy. In this paper, we present SocInf and focus on the fundamental problem known as membership inference. The key idea of SocInf is to construct a mimic model which has a similar prediction behavior with the public model, and then we can disclose the prediction differences between the training and testing data set by abusing the mimic model. With elaborated analytics on the predictions of the mimic model, SocInf can thus infer whether a given record is in the victim model's training set or not. We empirically evaluate the attack performance of SocInf on machine learning models trained by Xgboost, logistics, and online cloud platform. Using the realistic data, the experiment results show that SocInf can achieve an inference accuracy and precision of 73% and 84%, respectively, in average, and of 83% and 91% at best.

Energy efficient broadcasting is of paramount importance for many broadcast applications in wireless ad hoc networks. With respects network coding, it has been proved that the energy gain is upper bounded by 3. However, the coding opportunity is often highly dependent on the established routing paths, resulting in that a lot of coding opportunities could be lost in practice. By combining network coding with the Connected Dominating Set (CDS)-based broadcasting, we take full use of network coding. The intuition behind our algorithm is to intersect information flows at nodes in CDS to increase the coding opportunities. We propose a novel scheme named NCAB, a Network Coding Aware based Broadcast routing mechanism, integrating the network coding and the dynamic implementation of connected dominating set. Our experimental results show that NCAB provides up to 169% gains compared to flooding, and 41% gains compared to CDS-based broadcasting.

Routing is one of the most challenging open problems in pocket-switched-networks (PSN). In this paper, we propose a novel co-route media content forwarding scheme (CRMF), in which new contact opportunities are created for occasionally disconnected mobile users. Our study is inspired by two observations: one is that many people tend to make regular journeys to the same place, so their trajectories show a high degree of temporal and spatial regularity. The other is that the number of repeated journeys for an individual commuter is greater than that of the repeated contacts with another commuter who possess similar seasonal movement patterns. Our main contributions include: we properly install store-and-forward routers based on vehicle mobility patterns and human regular movement behaviors; we also propose a router-centric prediction scheme that collects passenger historical trajectory information to determine the delivery scheme. The simulation results demonstrate that this approach improves delivery ratio and also reduces the delivery latency compared to memory (history)-less delivery scheme.