Eclipse attacks, which isolate victim nodes by monopolizing their peer connections, remain a critical threat to Ethereum’s consensus mechanism. To address this, we present a principled framework for detecting Eclipse attacks in Ethereum peer-to-peer networks, grounded in a formal adversarial model. Existing defenses are either ad-hoc or lack provable guarantees, leaving open questions about their reliability under adaptive adversaries. Our work aims to bridge this gap by formally defining eclipse attack detection as a security property. We specify soundness, completeness, and robustness theorems under bounded adversarial drift, and derive formal guarantees within false positive and false negative bounds, resilience to adversarial manipulation, and multi-node compositional reliability. We then instantiate a lightweight detection framework that maps packet-level traffic features to predictions using ensemble classifiers (Random Forest, XGBoost). The system was validated using a controlled Ethereum testbed and extended with CTGAN-generated synthetic traces to emulate networks of up to 100 nodes. Empirical evaluation shows that our framework achieves up to 96% F1-score with sub-second inference latency, well within Ethereum’s 12-second Proof-of-Stake validator time slots. These findings demonstrate that lightweight statistical features, when coupled with formal analysis, enable accurate, efficient, and scalable detection of network-level partitioning attacks. Our work establishes a deployable and theoretically grounded defense foundation for securing modern blockchain systems against eclipse adversaries.

Federated Learning (FL) has emerged as a privacy-preserving paradigm for training machine learning models across distributed edge devices in the Internet of Things (IoT). By keeping data local and coordinating model training through a central server, FL effectively addresses privacy concerns and reduces communication overhead. However, the limited computational power, memory, and bandwidth of IoT edge devices pose significant challenges to the efficiency and scalability of FL, especially when training deep neural networks. Various FL frameworks have been proposed to reduce computation and communication overheads through dropout or layer freezing. However, these approaches often sacrifice accuracy or neglect memory constraints. To this end, in this work, we introduce Federated Learning with Ordered Layer Freezing (FedOLF). FedOLF consistently freezes layers in a predefined order before training, significantly mitigating computation and memory requirements. To further reduce communication and energy costs, we incorporate Tensor Operation Approximation (TOA), a lightweight alternative to conventional quantization that better preserves model accuracy. Experimental results demonstrate that over non-iid data, FedOLF achieves at least 0.3%, 6.4%, 5.81%, 4.4%, 6.27% and 1.29% higher accuracy than existing works respectively on EMNIST (with CNN), CIFAR-10 (with AlexNet), CIFAR-100 (with ResNet20 and ResNet44), and CINIC-10 (with ResNet20 and ResNet44), along with higher energy efficiency and lower memory footprint.

With the rise of the smart industry, machine learning (ML) has become a popular method to improve the security of the Industrial Internet of Things (IIoT) by training anomaly detection models. Federated learning (FL) is a distributed ML scheme that facilitates anomaly detection on IIoT by preserving data privacy and breaking data silos. However, poisoning attacks pose significant threats to FL, where adversaries upload poisoned local models to the aggregation server, thereby degrading model accuracy. The prevalence of non-independent and identically distributed (non-IID) data across IIoT devices further exacerbates this threat, as it naturally leads to diverse local models, making malicious ones harder to distinguish. To address the above challenges, we propose a deep-layer sign-sharing personalized FL (DSPFL) scheme. DSPFL innovatively aggregates only the signs of stochastic gradients (SignSGD) from the deep layers of local models during training. This targeted aggregation enhances the robustness of the shared components against poisoning attacks, while shallow layers are retained locally to preserve personalization. This integrated approach improves the accuracy and resilience of personalized local models on IIoT devices under poisoning attacks. Extensive experimental results show that DSPFL consistently achieves up to 20% higher and more stable overall personalized model accuracy compared to state-of-the-art methods under specific poisoning attacks.

With the rapid development of blockchain technology, smart contract applications have become increasingly widespread. However, vulnerabilities in contracts may be exploited by attackers, causing serious financial losses. In recent years, learning-based approaches have gained prominence for their accuracy and efficiency by automatically extracting explicit syntactic or semantic features from a large number of smart contracts with minimal manual intervention. In this article, we conduct a comprehensive analysis and ultimately select 61 scientific publications to provide researchers, especially beginners, with a comprehensive understanding of the learning-based detection process and guidance on selecting appropriate code representations. We first introduce common types of vulnerabilities, detail uncovered vulnerabilities, and summarize datasets used in learning-based methods. Then, we elaborate on the general process of learning-based detection and classify existing publications based on code representations, including sequence, tree, graph, and mixed features. Finally, we summarize the progress of existing work and explore future research directions in this field.

Sybil attacks pose a significant threat to federated learning, as malicious nodes can collaborate to form a majority and overwhelm the system. Therefore, developing effective countermeasures is essential to ensure the security of federated learning systems. To address this challenge, we introduce a novel targeted model poisoning defence method for federated learning, named Gradient Drift Detection (FedGDD). Unlike existing approaches, such as clustering, statistical analysis, and re-training, which struggle in scenarios where malicious nodes constitute the majority, FedGDD reframes malicious detection as a gradient drift detection problem. This approach identifies potential attacks by detecting deviations in gradients, operating on the premise that the loss functions for benign and malicious nodes are inherently different. Extensive experimental evaluations demonstrate the efficacy of FedGDD compared to six well-established methods: Flame, FLTrust, FedCPA, Median, Krum, and FL-WBC. Using tasks from both image classification and natural language processing, the experiments confirm that FedGDD is robust and independent of specific application settings. Results show that FedGDD effectively safeguards federated learning systems across a wide range of malicious node ratios. Specifically, FedGDD maintains a low attack success rate for malicious nodes when their ratio ranges from 0.2 to 0.8. Additionally, it preserves high model accuracy when the malicious node ratio is between 0.2 and 0.5. These findings highlight FedGDD's potential to enhance the reliability and performance of Federated Learning systems.

We propose Meta-DPMAPPO /metə,dipi'mæpəʊ/, a a metaverse multi-user service migration framework that combines Multi-Agent Proximal Policy Optimization (MAPPO) with Differential Privacy (DP)-enabled dual-domain perturbation. To maintain usability, we incorporate trajectory topology constraints that balance privacy strength with data availability. The framework enables dynamic service migration, i.e., transferring services to follow mobile users, to ensure low-latency access while safeguarding sensitive user data. We design a migration strategy with multiple migration actions (i.e.,reuse,follow, andnomigration) to minimize global delay and improve resource utilization. We conduct a series of experiments using a combination of public, collected, and synthetic datasets. The results demonstrate that our approach significantly reduces global migration delay in multi-user environments while ensuring privacy protection, and adapts well to different metaverse application scenarios.

The metaverse is a pioneering cyber-physical space that seamlessly blends the physical and virtual worlds, demanding a fully immersive and highly interactive user experience. However, existing communication designs and traditional offloading and allocation approaches fall short of meeting the dynamic network conditions and real-time performance demands of the metaverse. To tackle these challenges, we develop a wireless transmission architecture optimized for metaverse computation offloading and resource allocation. This design leverages the Rayleigh fading and Multiple Input Multiple Output (MIMO) technology to optimize transmission paths, enhancing the reliability and efficiency of signal transmission in high-concurrency connections. We further introduce MetaTMCO (MetaTransformer andMAPPO basedComputationOffloading), a dynamic online computation offloading and resource allocation joint optimized method that meets critical QoS requirements for metaverse applications. MetaTMCO uses a metric named Interaction Frequency (IF) to evaluate resource competition between users and resource interaction between users and the environment, combining QoS to maximize utility under resource constraints. By integrating a Transformer-based encoder-decoder within the Multi-Agent Proximal Policy Optimization (MAPPO) algorithm, MetaTMCO mitigates inefficiencies from partial observations, enabling dynamic optimization of real-time fast offloading strategies across multiple agents. Experimental results demonstrate that MetaTMCO significantly outperforms other approaches in metaverse environments, achieving superior strategy optimization and resource efficiency.

Personalized Federated Learning (PFL) is widely employed in the Internet of Things (IoT) to handle high-volume, non-iid client data while ensuring data privacy. However, heterogeneous edge devices owned by clients may impose varying degrees of resource constraints, causing computation and communication bottlenecks for PFL. Federated Dropout has emerged as a popular strategy to address this challenge, wherein only a subset of the global model, i.e. a sub-model, is trained on a client's device, thereby reducing computation and communication overheads. Nevertheless, the dropout-based model-pruning strategy may introduce bias, particularly towards non-iid local data. When biased sub-models absorb highly divergent parameters from other clients, performance degradation becomes inevitable. In response, we propose federated learning with stochastic parameter update (FedSPU). Unlike dropout that tailors local models to small-size sub-models, FedSPU maintains the full model architecture on each device but randomly freezes a certain percentage of neurons in the local model during training while updating the remaining neurons. This approach ensures that a portion of the local model remains personalized, thereby enhancing the model's robustness against biased parameters from other clients. Experimental results demonstrate that FedSPU outperforms federated dropout by 4.45% on average in terms of accuracy. Furthermore, an introduced early stopping scheme leads to a significant reduction of the training time in FedSPU by 25%~71% while maintaining high accuracy.

We propose a new workflow task execution time prediction approach, DAG-FGL, by integrating Flash attention mechanism with a GraphLSTM model. It addresses the challenge of low task execution time prediction accuracy in the presence of complex dependencies among workflow subtasks. The GraphLSTM model captures and conveys subtask dependencies through the adjacency matrix of sub task relationships modeled as a directed acyclic graph (DAG). The Flash attention mechanism enhances the model by incorporating customized positional encoding of subtask priority. The encoding ensures that the model accurately reflects each subtask's importance and relative order when calculating attention weight. Therefore, DAG- FG L can more accurately predict task execution time in the context of complex dependencies. Experimental results show that DAG-FGL outperforms the best-performing baseline model. It achieves 7.82 % to 44.52 % improvements in prediction accuracies over the best-performing baselines across three cloud workflow datasets of varying lengths.

Mobile edge computing (MEC) enables cooperative vehicle infrastructure systems (CVIS) to provide computational services to vehicles via roadside units. However, the increasing complexity of intelligent vehicles leads to the generation of numerous delay-sensitive tasks, presenting significant challenges for computation offloading. Furthermore, frequent interactions between intelligent vehicles and servers during the offloading process exacerbate privacy risks. In this paper, we propose a novel resource discovery approach, which determines the priority of offloading tasks based on an incentive strategy and constructs a task queue to optimize resource utilization. To facilitate optimal task offloading decisions, we employ a federated reinforcement learning algorithm that integrates dynamic differential privacy, addressing the dynamic nature of privacy protection requirements and enhancing the security of edge nodes. Through simulation, we demonstrate that our proposed algorithm outperforms traditional approaches by effectively reducing task execution latency and preserving vehicular privacy. The experimental findings highlight the potential of our approach to significantly improve task offloading performance in CVIS.

As the Metaverse evolves, robust authentication is essential to protect digital avatar privacy from identity threats such as theft, unauthorized access, and avatar spoofing. A user’s gait, serving as an intrinsic biometric signature of their avatar, offers a seamless and continuous authentication mechanism, enhancing security. Traditional authentication methods, including passwords, biometrics, and facial or fingerprint recognition, face challenges in virtual environments due to occlusions, spoofing risks, and hardware dependencies. To address these limitations, we introduce AutoGaitAnalyzer, a novel gait authentication framework that uses 16 gait features from a large-scale simulation of 5,000 users. Benchmarked against over 10 state-of-the-art models, AutoGaitAnalyzer outperforms all, establishing a new standard for avatar security in the Metaverse.

Autonomous vehicles generate massive volumes of point cloud data, yet only a subset is relevant for specific tasks such as collision detection, traffic analysis, or congestion monitoring. Effectively querying this data is essential to enable targeted analytics. In this work, we formalize point cloud querying by defining three core query types: RETRIEVAL, COUNT, and AGGREGATION, each aligned with distinct analytical scenarios. All these queries rely heavily on accurate object counts to produce meaningful results, making precise object counting a critical component of query execution. Prior work has focused on indexing techniques for 2D video data, assuming detection models provide accurate counting information. However, when applied to 3D point cloud data, state-of-the-art detection models often fail to generate reliable object counts, leading to substantial errors in query results. To address this limitation, we propose CounterNet, a heatmap-based network designed for accurate object counting in large-scale point cloud data. Rather than focusing on accurate object localization, CounterNet detects object presence by finding object centers to improve counting accuracy. We further enhance its performance with a feature map partitioning strategy using overlapping regions, enabling better handling of both small and large objects in complex traffic scenes. To adapt to varying frame characteristics, we introduce a per-frame dynamic model selection strategy that selects the most effective configuration for each input. Evaluations on three real-world autonomous vehicle datasets show that CounterNet improves counting accuracy by 5% to 20% across object categories, resulting in more reliable query outcomes across all supported query types.

Point clouds are essential for object modeling and play a critical role in assisting driving tasks for autonomous vehicles (AVs). However, the significant volume of data generated by AVs creates challenges for storage, bandwidth, and processing cost. To tackle these challenges, we propose a representative point selection framework for point cloud downsampling, which preserves critical object-related information while effectively filtering out irrelevant background points. Our method involves two steps: (1) Object Presence Detection, where we introduce an unsupervised density peak-based classifier and a supervised Naïve Bayes classifier to handle diverse scenarios, and (2) Sampling Budget Allocation, where we propose a strategy that selects object-relevant points while maintaining a high retention rate of object information. Extensive experiments on the KITTI and nuScenes datasets demonstrate that our method consistently outperforms state-of-the-art baselines in both efficiency and effectiveness across varying sampling rates. As a model-agnostic solution, our approach integrates seamlessly with diverse downstream models, making it a valuable and scalable addition to the 3D point cloud downsampling toolkit for AV applications.

Deep learning (DL) components have been broadly applied in diverse applications. Similar to traditional software engineering, effective test case generation methods are needed by industry to enhance the quality and robustness of these deep learning components. To this end, we propose a novel automatic software testing technique, TAEFuzz (Automatic Fuzz -Testing via T ransferable A dversarial E xamples), which aims to automatically assess and enhance the robustness of image-based deep learning (DL) systems based on test cases generated by transferable adversarial examples. TAEFuzz alleviates the over-fitting problem during optimized test case generation and prevents test cases from prematurely falling into local optima. In addition, TAEFuzz enhances the visual quality of test cases through constraining perturbations inserted into sensitive areas of the images. For a system with low robustness, TAEFuzz trains a low-cost denoising module to reduce the impact of perturbations in transferable adversarial examples on the system. Experimental results demonstrate that the test cases generated by TAEFuzz can discover up to 46.1% more errors in the targeted systems, and ensure the visual quality of test cases. Compared to existing techniques, TAEFuzz also enhances the robustness of the target systems against transferable adversarial examples with the perturbation denoising module.

Given that smart contracts execute transactions worth hundreds of millions of dollars daily, the issue of smart contract security has attracted considerable attention over the past few years. Traditional methods for detecting vulnerabilities heavily rely on manually developed rules and features, leading to the problems of low accuracy, high false positives, and poor scalability. Although deep learning-inspired approaches were designed to alleviate the problem, most of them rely on monothetic features, which may result in information incompetence during the learning process. Furthermore, the lack of available labeled vulnerability datasets is also a major limitation. To address these issues, we collect and construct a dataset of five labeled smart contract vulnerabilities, and proposeDeepFusion, a vulnerability detection method that fuses code representation information, including program slice information and abstraction syntax tree (AST) structured information. First, we develop automated tools to extract contract vulnerability slicing information from source code, and extract structured information from source code-converted AST. Second, code features and global structured features are fused into the data. Finally, the fused data are input into the Bidirectional Long Short-Term Memory+ Attention (BiLSTM+ATT) model for smart contract vulnerability detection. The BiLSTM model can capture long-term dependencies in both directions and is more suitable for processing serialized information generated byDeepFusion, while the attention mechanism can highlight the characteristic information of vulnerabilities. We conducted experiments via collecting a real smart contract dataset. The experimental results show that our method significantly outperforms the existing methods in detecting the vulnerabilities ofreentrancy,timestamp dependence,integer overflow and underflow,Use tx.origin for authentication, andUnprotected Self-destruct Instructionby 6.36%, 6.42%, 16.5%, 21.29%, and 25.05%, respectively. To the best of our knowledge, the latter two vulnerabilities are the first to be detected using deep learning methods.

In mobile edge computing (MEC), mobile users can offload tasks to edge nodes to alleviate local computational loads, leveraging the computing capabilities of edge nodes. However, users' high mobility and temporal variability pose challenges in dynamically allocating mobile users to optimize perceived Quality of Service (QoS). To address this challenge, this paper proposes an adaptive ant colony algorithm for user allocation decisions. This method constructs hidden mobility fitness relationships between users and servers based on user movement trajectories. It utilizes an improved adaptive ant colony algorithm to adjust fitness values automatically and optimize user allocation. The goal is to maximize overall user satisfaction under resource constraints while minimizing user allocation costs. Experimental analysis demonstrates that the proposed method achieves higher user allocation rates and effectively utilizes available resources on edge servers.

The widespread use of deep neural networks (DNNs) in image classification sofwares underlines the importance of the robustness. Researchers have proposed sparse adversarial attack methods for generating test cases, which add pixel-level perturbations to construct the test case to mislead the target model. However, the existing methods have certain limitations, such as high time cost, poor flexibility, and poor quality of the test cases. To address these issues, we propose a gradient-guided test case generation method (GGTM) to evaluate the robustness of image classification software. The method firstly identifies the key region in the image based on the gradient-weighted class activation mapping (Grad-CAM) and the prediction confidence of the target model on the input image. In the key region, it selects a set of pixels as candidate perturbation pixels according to the gradient value and the change of loss function. Then perturbations are added to the candidate perturbation pixels after applying a random dropout strategy to reduce some candidate perturbation pixels which is used to avoid local optimum. For the initially constructed test case which can mislead the target model, after removing redundant and unimportant perturbations, perturbations are re-added to optimize the test case. Experiments show the effectiveness of GGTM, which achieves 100% attack success rate. And the test cases generated by GGTM have the best perturbation sparsity. Furthermore, compared with the baseline method SparseAG which achieves optimal perturbation sparsity among the baseline methods, GGTM significantly improves the efficiency.

With the growing prevalence of deep learning in the speech area, speech recognition, voice control, and related applications have become integral parts of people's lives. However, the rise of malicious third-party platforms has introduced significant security concerns, particularly through backdoor attacks. These attacks implant triggers that manipulate speech recognition models to produce specific labels, thereby compromising the system's integrity. Studying speech backdoor attacks is crucial for evaluating the security of speech recognition software, and iden-tifying and addressing potential vulnerabilities. Existing methods for speech backdoor attacks usually employ fixed perturbations as triggers. However, these perturbations may be discernible to the human ear, making them easily detectable. To address this issue, we propose a frequency domain-embedded backdoor attack method based on echo hiding. Echo hiding is a steganography technique based on audio. This method embeds hidden information into the frequency spectrum of the echo signal, leveraging the masking property of the human auditory system. It is difficult to arouse suspicion or detect the presence of hidden information since echo is perceived as a natural phenomenon in auditory perception. Furthermore, it does not cause a significant decrease in audio quality. Experimental results show the effectiveness of our method in different settings.

Scribble-supervised semantic segmentation presents a cost-effective training method that utilizes annotations generated through scribbling. It is valued in attaining high performance while minimizing annotation costs, which has made it highly regarded among researchers. Scribble supervision propagates information from labeled pixels to the surrounding unlabeled pixels, enabling semantic segmentation for the entire image. However, existing methods often ignore the features of classified pixels during feature propagation. To address these limitations, this paper proposes a prototype-based feature augmentation method that leverages feature prototypes to augment scribble supervision. Experimental results demonstrate that our approach achieves state-of-the-art performance on the PASCAL VOC 2012 dataset in scribble-supervised semantic segmentation tasks. The code is available at https://github.com/TranquilChan/PFA.

The emergence of the metaverse signifies a paradigm shift in Internet technology, offering a comprehensive virtual social platform spanning various domains such as social interaction, gaming, healthcare, and tourism. This new era of the metaverse is facilitated by advancements in next-generation digital technologies including edge computing, artificial intelligence, virtual reality, augmented reality, and blockchain. In the metaverse, the quantity and variety of services requested by users may surpass those in other environments, and existing work cannot be applied to metaverse QoS (Quality of Service) optimization. To address this problem, this paper proposes Meta-PPO, an optimization method for enhancing the QoS of metaverse services using reinforcement learning. Firstly, metaverse services are categorized into virtual scene services and meta-services, providing a comprehensive framework for analysis. Secondly, Meta-PPO, based on the proximal policy optimization algorithm, is introduced to optimize the QoS of metaverse services. This method effectively balances the objectives of minimizing average delay and maximizing resource utilization of mobile devices by making informed offloading decisions for the identified service categories. Simulation results demonstrate the superiority of the proposed method over existing techniques, showcasing its suitability and effectiveness for enhancing the QoS of metaverse service.

Mobile edge computing (MEC) relies on offloading tasks to edge nodes to avoid delays and failures caused by local computing. However, developing efficient offloading decisions is challenging, as it involves addressing the intricacies of tasks and the instability of edge node resources(e.g. available computer resources, memory, and bandwidth). In this paper, we propose a novel approach to tackle the problem of task offloading. Our approach involves dividing tasks into smaller units and considering the correlations between these sub-tasks. To make optimal offloading decisions, we employ a deep reinforcement learning algorithm that takes into account user movement patterns and the availability of resources at edge nodes. Through simulations, we demonstrate that our proposed algorithm outperforms several existing algorithms in terms of offloading decisions. It effectively reduces task execution delays and energy costs. These findings highlight the potential of our approach in improving the performance of task offloading in MEC systems.

The Internet of Things (IoT) has become increasingly prevalent in various aspects of our lives, enabling billions of devices to connect and communicate seamlessly. However, the intricate nature of IoT connections and device vulnerabilities exposes the devices to security threats. To address the security challenges, we propose a proactive defense framework that leverages a model-based approach for security analysis and facilitates the defense strategies. Our proposed approach incorporates proactive defense mechanisms that combine Moving Target Defense techniques with cyber deception. The proposed approach involves the use of a decoy nodes as a deception technique and operating system based diversity as a moving target defense strategy to change the attack surface area of IoT networks. Additionally, we introduce a technique known as Important Measure-based Operating System Diversity to reduce defense cost. The effectiveness of the defense mechanisms was evaluated by using a graphical security model in a Software Defined Networking-based IoT network. Simulation results demonstrate the effectiveness of our approach in mitigating the impact of attacks while maintaining high performance levels in IoT networks.

Abstract The growing popularity of smart contracts in various areas, such as digital payments and the Internet of Things, has led to an increase in smart contract security challenges. Researchers have responded by developing vulnerability detection tools. However, the effectiveness of these tools is limited due to the lack of authentic smart contract vulnerability datasets to comprehensively assess their capacity for diverse vulnerabilities. This paper proposes a Deep Learning‐based Smart contract vulnerability Generation approach (SGDL) to overcome this challenge. SGDL utilizes static analysis techniques to extract both syntactic and semantic information from the contracts. It then uses a classification technique to match injected vulnerabilities with contracts. A generative adversarial network is employed to generate smart contract vulnerability fragments, creating a diverse and authentic pool of fragments. The vulnerability fragments are then injected into the smart contracts using an abstract syntax tree to ensure their syntactic correctness. Our experimental results demonstrate that our method is more effective than existing vulnerability injection methods in evaluating the contract vulnerability detection capacity of existing detection tools. Overall, SGDL provides a comprehensive and innovative solution to address the critical issue of authentic and diverse smart contract vulnerability datasets.

Abstract With the widespread application of smart contracts, there is a growing concern over the quality assurance of smart contracts. The data flow testing is an important technology to ensure the correctness of smart contracts. We propose an approach named IABC‐TCG (Improved Artificial Bee Colony‐Test Case Generation) to generate test cases for the data flow testing of smart contracts. With a dominance relations‐based fitness function, an improved artificial bee colony algorithm is used to generate test cases, in which the bee colony search coefficient is adaptively adjusted to improve the effectiveness and efficiency of the search. In addition, an improved test case selection and updation strategy is used to avoid unnecessary test cases. The experimental results show that IABC‐TCG achieves 100% coverage for all the test requirements on a dataset of 30 smart contracts and outperforms the baseline approaches in terms of the number of test cases and the execution time. Performing tests with the generated test cases, IABC‐TCG can find more errors with less test cost.

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where the adversaries can implant malicious prediction behaviors into victim models by poisoning their training process. In this paper, we revisit poison-only backdoor attacks against speech recognition. We reveal that existing methods are not stealthy since their trigger patterns are perceptible to humans or machine detection. This limitation is mostly because their trigger patterns are simple noises or separable and distinctive clips. Motivated by these findings, we propose to exploit elements of sound (e.g., pitch and timbre) to design more stealthy yet effective poison-only backdoor attacks. Specifically, we insert a short-duration high-pitched signal as the trigger and increase the pitch of remaining audio clips to ‘mask’ it for designing stealthy pitch-based triggers. We manipulate timbre features of victim audio to design the stealthy timbre-based attack and design a voiceprint selection module to facilitate the multi-backdoor attack. Our attacks can generate more ‘natural’ poisoned samples and therefore are more stealthy. Extensive experiments are conducted on benchmark datasets, which verify the effectiveness of our attacks under different settings (e.g., all-to-one, all-to-all, clean-label, physical, and multi-backdoor settings) and their stealthiness. Our methods achieve attack success rates of over 95% in most cases and are nearly undetectable. The code for reproducing main experiments are available at https://github.com/HanboCai/BadSpeech_SoE.

With the rapid development of 5G technologies, the demand of quality of service (QoS) from edge users, including high bandwidth and low latency, has increased dramatically. QoS within a mobile edge network is highly dependent on the allocation of edge users. However, the complexity of user movement greatly challenges edge user allocation, leading to privacy leakage. In addition, updating massive data constantly in a dynamic mobile edge network also crucial to ensure efficiency. To address these challenges, this paper proposes a dynamic QoS optimization strategy (MENIFLD_QoS) in mobile edge networks based on incremental learning and federated learning.MENIFLD_QoSoptimizes service cache in edge regions and allocates edge servers to edge users according to the locations of edge servers accessed by edge users in mobile scenarios. While optimizing regional service quality, the system can effectively protect user privacy. In addition, for dynamic incremental data,MENIFLD_QoStrains updated data based on the strategy of incremental learning hence significantly improves optimization speed. Experimental results on an edge QoS dataset show that the proposed strategy achieves global optimization in both multi-variable and multi-peak user allocation scenarios and notably enhances the training efficiency of the regional invocation model.

Federated Learning (FL) achieves great popularity in the Internet of Things (IoT) as a powerful interface to offer intelligent services to customers while maintaining data privacy. Under the orchestration of a server, edge devices (also called clients in FL) collaboratively train a global deep-learning model without sharing any local data. Nevertheless, the unequal training contributions among clients have made FL vulnerable, as clients with heavily biased datasets can easily compromise FL by sending malicious or heavily biased parameter updates. Furthermore, the resource shortage issue of the network also becomes a bottleneck. Due to overwhelming computation overheads generated by training deep-learning models on edge devices, and significant communication overheads for transmitting deep-learning models across the network, enormous amounts of resources are consumed in the FL process. This encompasses computation resources like energy and communication resources like bandwidth. To comprehensively address these challenges, in this paper, we present FLrce, an efficient FL framework with arelationship-basedclient selection andearly-stopping strategy. FLrce accelerates the FL process by selecting clients with more significant effects, enabling the global model to converge to a high accuracy in fewer rounds. FLrce also leverages an early stopping mechanism that terminates FL in advance to save communication and computation resources. Experiment results show that, compared with existing efficient FL frameworks, FLrce improves the computation and communication efficiency by at least 30% and 43% respectively.

This paper presents a novel probabilistic Quality of Service (QoS) monitoring method named DLSTM-BRPM (Double Long Short Term Memory (DouLSTM-Den) based Bayesian Runtime Proactive Monitoring) to accurately and efficiently monitor QoS in a mobile edge environment. This method consists of a DouLSTM-Den model and a Gaussian Hidden Bayesian classifier. The DouLSTM-Den model aims to predict a user’s future movement trajectory in real time and proactively monitor the spatio-temporal QoS performance of services based on the predicted trajectory. The Gaussian Hidden Bayesian classifier is employed to accurately monitor QoS by constructing parent attributes to reduce the interdependence between QoS attributes. Our experiments based on public synthetic datasets demonstrate the effectiveness of the proposed method over state-of-the-art solutions. We also conducted experiments in a real-world edge environment to validate the feasibility of the proposed method.

We propose a novel approach to effectively detect cloned identities of social-sensor cloud service providers (i.e. social media users) in the face of incomplete non-privacy-sensitive profile data. Named ICD-IPD, the proposed approach first extracts account pairs with similar usernames or screen names from a given set of user accounts collected from a social media. It then learns a multi-view representation associated with a given account and extracts two categories of features for every single account. These two categories of features include profile and Weighted Generalised Canonical Correlation Analysis (WGCCA)-based features that may potentially contain missing values. To counter the impact of such missing values, a missing value imputer will next impute the missing values of the aforementioned profile and WGCCA-based features. After that, the proposed approach further extracts two categories of augmented features for each account pair identified previously, namely, 1) similarity and 2) differences-based features. Finally, these features are concatenated and fed into a Light Gradient Boosting Machine classifier to detect identity cloning. We evaluated and compared the proposed approach against the existing state-of-the-art identity cloning approaches and other machine or deep learning models atop a real-world dataset. The experimental results show that the proposed approach outperforms the state-of-the-art approaches and models in terms of Precision, Recall and F1-score.

We propose an innovative approach named MEC-RDESN /mek”r:dI’saIn/ (MECQoS forecasting based onRegion recognition andDynamicEchoStateNetwork) enabling mobility-aware and swift QoS forecasting in the mobile edge computing environment. MEC-RDESN offers efficient QoS forecasting while maintaining high accuracy. We can identify the edge region to which a user belongs in real time while moving by leveraging mobile sensing technology. We employ adynamic echo state networkcharacterized by multi-service adaptability to retain information about services invoked by users to ensure real-time training and forecasting accuracy. Our approach is validated through a series of experiments using both public and collected datasets. The experiments demonstrate that MEC-RDESN achieves the goal of fast forecasting while ensuring its forecasting accuracy in diverse application scenarios.

Federated learning provides privacy protection to the collaborative training of global model based on distributed private data. The local private data is often in the presence of long-tailed distribution in reality, which downgrades the performance and causes biased results. In this paper, we propose a dynamic adaptive federated learning optimization algorithm with the Grey Wolf Optimizer and Markov Chain, named FedWolf, to solve the problems of performance degradation and result bias caused by the local long-tailed data. FedWolf is launched with a set of randomly initialized parameters instead of a shared parameter employed by existing methods. Then multi-level participants are elected based on the F1 scores calculated from the uploaded parameters. A dynamic weighting strategy based on the participant level is used to adaptively update parameters without artificial control. The above parameter updating is modelled as a Markov Process. After all communication rounds are completed, the future performance (including the probability of each participant is elected as different participant level) of participants is predicted through the historical Markov states. Finally, the probability of each participant is elected as the level 1 is used as the contribution weight and the global model is obtained through dynamic contribution weight aggregating. We introduce the Gini index to evaluate the bias of classification results. Extensive experiments are conducted to validate the effectiveness of FedWolf in solving the problems of performance cracks and categorization result bias as well as the robustness of adaptive parameter updating in resisting outliers and malicious users.

With the rise of 5G technology, Mobile (or Multi-Access) Edge Computing (MEC) has become crucial in modern network architecture. One key research area is the effective placement of edge nodes, which has attracted significant attention. Service providers strive to minimize deployment costs for these nodes within a network. Although many studies have explored optimal strategies for reducing these costs, most overlook the allocation of computational resources and the users’ tolerance for delays. These factors add complexity, making previous methods less adaptable. In this paper, we define the Cost Minimization in MEC Edge Node Placement problem. Our goal is to find the optimal strategy for deploying edge nodes that minimize costs while cater to users’ delay tolerance limits. We prove the NP-hardness of this problem and provide a range of solutions, including Cluster-based Mixed Integer Programming, Coverage First Search, and Distance-Aware Coverage First Search, to address this challenge effectively and efficiently. Additionally, we propose a fine-grained optimization approach for allocating computational resources to edge nodes based on user service requests, significantly lowering deployment costs. Extensive experiments on a large-scale real-world dataset show that our solutions outperform the state-of-the-art in efficiency, effectiveness, and scalability.

Mobile devices commonly offload latency-sensitive applications to edge servers to meet low-latency requirements. However, existing studies overlook dependency and application hit ratio considerations, hindering effective offloading for multi-applications and multi-tasks. To this end, this article proposes a Dependent task offloading and Service placement Optimization (DSO) method to maximize the application hit ratio, thereby providing high-quality service. The proposed DSO includes Improved Multi-Agent Q-Learning (IMAQL) and greedy algorithms. IMAQL optimizes service placement via Q-learning, while the greedy algorithm schedules task offloading. Extensive experiments on public datasets demonstrate that the DSO method enhances the application hit ratio by 4.7% to 11.7% and reduces the completion time by about 3.4% to 4.9% compared to alternative approaches.

Although many tools have been developed to detect anomalies in smart contracts, the evaluation of these analysis tools has been hindered by the lack of adequate anomalisticreal-world contracts(i.e., smart contracts with addresses on Ethereum to achieve certain purposes). This problem prevents conducting reliable performance assessments on the analysis tools. An effective way to solve this problem is to inject anomalies intoreal-world contractsand automatically label the locations and types of the injected anomalies.SolidiFI, as the first and only tool in this area, was developed to automatically inject anomalies into Ethereum smart contracts. However,SolidiFIis subject to the limitations from its methodologies (e.g., its injection accuracy and authenticity are low). To address these limitations, we propose an approach calledSCAnoGenerator.SCAnoGeneratorsupports Solidity 0.5.x, 0.6.x, 0.7.x and enables automatic anomaly injection for Ethereum smart contracts via analyzing the contracts’ control and data flows. Based on this approach, we develop an open-source tool, which can inject 20 types of anomalies into smart contracts. The extensive experiments show thatSCAnoGeneratoroutperformsSolidiFIon the number of injected anomaly types, injection accuracy, and injection authenticity. The experimental results also reveal that existing analysis tools can only partially detect the anomalies injected bySCAnoGenerator.

We propose a federated learning-based data-driven trust prediction method to meet the demand of high-accuracy IoT service trustworthiness prediction in Mobile Edge Computing (MEC) with low convergence time. Our research focuses on the mixture distribution and heterogeneity features of IoT trust information in distributed MEC environments and formulates the task of distributed IoT trust prediction on top of MEC network topologies as a federated optimization problem. We then employ Federated Expectation-Maximization to mitigate the federated optimization problem by taking into account the data mixture distribution and heterogeneity. We conduct a series of experiments upon simulated MEC-based IoT environments crafted on top of a real-world IoT dataset. The experimental results show that our proposed methods can achieve better balance between prediction accuracy and model training efficiency than a state-of-the-art data-driven MEC-based IoT service trust prediction method and a Federated Averaging-based method.

The blockchain ecosystem is expanding as a result of advancements in blockchain technology and the emergence of BaaS (Blockchain as a Service) platforms. Smart contracts are designed to carry out diverse business operations, but there is a risk of Ponzi schemes being concealed within them. These schemes masquerade as investment agreements and deceive users, resulting in substantial losses for the blockchain community. Detecting Ponzi schemes in smart contracts is crucial. This study introduces a machine learning approach to identify Ponzi schemes by extracting features from smart contracts using the control flow graph. During the construction of the control flow graph for the smart contract’s bytecode, elements unrelated to its functionality are identified and eliminated. We utilize the control flow graph to extract n-gram Term Frequency and n-gram Term Frequency-Inverse Document Frequency features. These features are respectively employed to construct a Random Forest model for Ponzi scheme detection. To address the issue of imbalanced samples, the SVM_SMOTE oversampling algorithm is applied to balance the number of positive and negative samples. The results from experiments conducted on a real-world dataset demonstrate the effectiveness of our approach. The feature extraction method based on the control flow graph outperforms the method based on continuous text. Additionally, the Random Forest model utilizing SVM_SMOTE outperforms four existing models.

The widespread adoption of DNNs in NLP software has highlighted the need for robustness. Researchers proposed various automatic testing techniques for adversarial test cases. However, existing methods suffer from two limitations: weak error-discovering capabilities, with success rates ranging from 0% to 24.6% for BERT-based NLP software, and time inefficiency, taking 177.8s to 205.28s per test case, making them challenging for time-constrained scenarios. To address these issues, this paper proposes LEAP, an automated test method that uses LEvy flight-based Adaptive Particle swarm optimization integrated with textual features to generate adversarial test cases. Specifically, we adopt Levy flight for population initialization to increase the diversity of generated test cases. We also design an inertial weight adaptive update operator to improve the efficiency of LEAP's global optimization of high-dimensional text examples and a mutation operator based on the greedy strategy to reduce the search time. We conducted a series of experiments to validate LEAP's ability to test NLP software and found that the average success rate of LEAP in generating adversarial test cases is 79.1%, which is 6.1% higher than the next best approach (PSOattack). While ensuring high success rates, LEAP significantly reduces time overhead by up to 147.6s compared to other heuristic-based methods. Additionally, the experimental results demonstrate that LEAP can generate more transferable test cases and significantly enhance the robustness of DNN-based systems.

Abstract Test case generation techniques based on adversarial examples are commonly used to enhance the reliability and robustness of image‐based and text‐based machine learning applications. However, efficient techniques for speech recognition systems are still absent. This paper proposes a family of methods that generate targeted adversarial examples for speech recognition systems. All are based on thefirefly algorithm (F), and are enhanced withgaussmutations and / orgradientestimation (F‐GM, F‐GE, F‐GMGE) to fit the specific problem of targeted adversarial test case generation. We conduct an experimental evaluation on three different types of speech datasets, includingGoogle Command,Common VoiceandLibriSpeech. In addition, we recruit volunteers to evaluate the performance of the adversarial examples. The experimental results show that, compared with existing approaches, these approaches can effectively improve the success rate of the targeted adversarial example generation. The code is publicly available at https://github.com/HanboCai/FGMGE .

Smart contracts are commonly deployed for safety-critical applications, the quality assurance of which has been a vital factor. Test cases are standard means to ensure the correctness of data flows in smart contracts. To more efficiently generate test cases with high coverage, we propose an improved genetic algorithm-based test-case generation approach for smart contract data flow testing. Our approach introduces the theory of particle swarm optimization into the genetic algorithm, which reduces the influence brought by the randomness of genetic operations and enhances its capability to find global optima. A set of 30 real smart contracts deployed on Ethereum and GitHub is collected to perform the experimental study, on which our approach is compared with three baseline approaches. The experimental results show that, in most cases, the coverage of the test cases generated by our approach is significantly higher than the baseline approaches with relatively lower numbers of iterations and lower execution time.

We propose a data-driven distributed machine learning approach to scalably predict the trustworthiness of homogeneous IoT services in heterogeneous Mobile Edge Computing (MEC)-based IoT systems. The proposed approach formulates training distributed trust prediction models within an MEC-based IoT system as a Network Lasso problem. We then introduce a variant of Stochastic Alternating Method of Multipliers framework (S-ADMM) enriched with the ability for feature selection at each MEC layer. To verify the effectiveness of the proposed approach, we carried out a comprehensive evaluation on three real-world datasets adjusted to exhibit the context-dependent trust information accumulated in MEC environments within a given MEC topology. The experimental results affirmed the effectiveness of our approach and its suitability to predict trustworthiness of IoT services in MEC-based IoT systems.

Mobile Edge Computing (MEC)-based Internet of Things (IoT) systems generate trust information in a real-time and distributed manner. Predicting trustworthiness of IoT services in such an MEC environment requires new prediction strategies that cater for the aforementioned characteristics of trust information. More importantly, it is imperative to investigate how the real-time trust information could be effectively integrated into trust prediction strategies in order to capture the ever-evolving nature of trustworthiness of IoT services. In turn, such a strategy allows IoT service consumers to derive more relevant and accurate trust-based decisions. To that end, our work models trust prediction in MEC-based IoT systems as an online regularized finite-sum problem in a distributed MEC environment with a given MEC topology. We then adopt the Online Alternating Direction Method (OADM) to effectively train trust prediction models in parallel over the distributed MEC environment. OADM allows splitting the aforementioned finite-sum problem into multiple sub-problems that correspond to different local MEC environments. These sub-problems can then be solved iteratively within each local MEC environment by using the local trust data therein. This can avoid the movement of data across the core networks of mobile network providers. Experiments on real-world and synthetic datasets demonstrate the effectiveness and scalability of the proposed method.

We propose a novel privacy-aware Quality of Service (QoS) forecasting approach in the mobile edge environment Edge-PMAM (Edge QoS forecasting with Public Model and Attention Mechanism). Edge-PMAM can make real-time, accurate and personalized QoS forecasting on the premise of user privacy preservation. Edge-PMAM comprises a public model for privacy-aware QoS forecasting in an edge region and a private model for personalized QoS forecasting for an individual user. An attention mechanism atop Long Short-Term Memory and an automated edge region division solution are devised to enhance the prediction accuracy of the public and private models. We conduct a series of experiments based on public and self-collected data sets. The results demonstrate that our approach can effectively improve forecasting performance and protect user privacy.

With the rising prominence of smart contracts, security attacks targeting them have increased, posing severe threats to their security and intellectual property rights. Existing simplistic datasets hinder effective vulnerability detection, raising security concerns. To address these challenges, we proposeBiAn, a source code level smart contract obfuscation method that generates complex vulnerability test datasets.BiAnprotects contracts by obfuscating data flows, control flows, and code layouts, increasing complexity and making it harder for attackers to discover vulnerabilities. Our experiments with buggy contracts showed an average complexity enhancement of approximately 174% after obfuscation. Decompilers Vandal and Gigahorse had total failure rate increments of 38.8% and 40.5% respectively. Obfuscated contracts also decreased vulnerability detection rates in more than 50% of cases for ten widely-used static analysis detection tools.

With the widespread use of smart contracts, security incidents caused by improper programming have drawn increasing attention. Data flow correctness is a fundamental and vital requirement for smart contracts. Although test cases generated by existing approaches for data flow testing of smart contracts can achieve certain coverage, not all def-use (definitionuse) pairs are covered, which may result in some errors not being detected. To further improve the adequacy and efficiency of testing, we present an approach named TCG-Re (T est C ase G eneration Combined with Data Flow R eduction) to generate test cases for data flow testing of smart contracts. Data flow reduction is performed to reduce redundant def-use pairs and obtain the final test requirements in a smart contract. The test case generation process is optimized to improve the coverage of the generated test cases for the def-use pairs. We collect 30 smart contracts of different scales to perform experimental evaluation. The result shows that, compared with other existing approaches, TCG-Re can not only achieve full coverage for most contracts, but also be more efficient. In addition, TCG-Re is also effective for discovering several types of errors in smart contracts.

Ethereum smart contracts face serious security problems, which not only cause huge economic losses, but also destroy the Ethereum credit system. To solve this problem, code obfuscation techniques are applied to smart contracts to improve their complexity and security. However, the current source code obfuscation methods have insufficient anti-decompilation ability. Therefore, we propose a novel bytecode obfuscation approach called BOSC based on four kinds of bytecode obfuscation techniques, which is directed at solidity. The experimental results show that, after the bytecode obfuscation, the failure rate of decompilation tools is over 99% and only a small amount of gas is consumed.

[J1C2 Presentation Abstract at IEEE SERVICES 2022 for IEEE Transactions on Services Computing DOI 10.1109/TSC.2020.2974741]

We propose a novel privacy-aware Quality of Service (QoS) forecasting approach in the mobile edge environment – Edge-PMAM (Edge QoS forecasting with Public Model and Attention Mechanism). Edge-PMAM can make realtime, accurate and personalized QoS forecasting on the premise of user privacy preservation. Edge-PMAM comprises a public model for privacy-aware QoS forecasting in an edge region and a private model for personalized QoS forecasting for an individual user. An attention mechanism atop Long Short-Term Memory and an automated edge region division solution are devised to enhance the prediction accuracy of the public and private models. We conduct a series of experiments based on public and self-collected data sets. The results based on public and self-collected data sets demonstrate that our approach can effectively improve forecasting performance and protect user privacy.

The extensive use of social media platforms and overwhelming amounts of imagery data creates unique opportunities for sensing, gathering and sharing information about events. One of its potential applications is to leveragecrowdsourcedsocial media images to create a tapestry scene for scene analysis of designated locations and time intervals. The existing attempts however ignore the temporal-semantic relevance and spatio-temporal evolution of the images and direction-oriented scene reconstruction. We propose a novel social-sensor cloud (SocSen) service composition approach to form tapestry scenes for scene analysis. The novelty lies in utilising images and image meta-information to bypass expensive traditional image processing techniques to reconstruct scenes. Metadata, such as geolocation, time, and angle of view of an image are modelled as non-functional attributes of a SocSen service. Our major contribution lies on proposing a context and direction-aware spatio-temporal clustering and recommendation approach for selecting a set of temporally and semantically similar services to compose the best available SocSen services. Analytical results based on real datasets are presented to demonstrate the performance of the proposed approach.

Quality of Service (QoS) is well acknowledged as a decisive means for ascertaining the performance of third-party Web services. QoS has high uncertainty in complex and dynamic network environments. QoS monitoring is considered as one of the most effective techniques to detect QoS violations at runtime. However, existing QoS monitoring approaches only consider single QoS attribute and do not provide a promising solution for comprehensively monitoring multivariate QoS attributes. To overcome this problem, a novel QoS monitoring approach, named M-BSRM (MultivariateBayeSianRuntimeMonitoring), is proposed. First, M-BSRM adopts the point mutual information theory to initialize the weights of different environmental impact factors and solves the problem of uneven distribution between classes brought by traditional algorithms. Second, each single QoS attribute is integrated with user preference using the information fusion theory. Finally, a Bayesian classifier is used to comprehensively evaluate multivariate QoS attributes at runtime. The experimental results on both the real-world and simulated data sets show that M-BSRM is more effective, practical, and efficient than the other approaches.

Mobile Edge Computing is an emerging technology offering low latency responses by deploying edge servers near mobile devices. We propose a novel privacy-preserving QoS forecasting approach – Edge-Laplace QoS (QoS forecasting with Laplace noise in mobile Edge environments) to address the challenges of user mobility and information leakage encountered by QoS forecasting in mobile edge environments. Edge-Laplace QoS is able to accurately and efficiently forecast Quality of Service (QoS) of various Web Services, while effectively protecting user privacy in mobile edge environments. We employ an improved differential privacy method to add dynamic disguises to the original QoS data in the edge environment to protect user data privacy. A collaborative filtering method is adopted to retrieve similar users’ accessing records based on geographic locations of their accessed servers for QoS forecasting. We conduct a set of experiments using several public network data sets. The results show that the efficiency of Edge-Laplace QoS is superior to traditional forecasting approaches. Edge-Laplace QoS is also validated to be more suitable for edge environments than traditional privacy-preserving approaches.

Deep Neural Network (DNN) driven technologies have been extensively employed in various aspects of our life. Nevertheless, the applied DNN always fails to detect erroneous behaviors, which may lead to serious problems. Several approaches have been proposed to enhance adversarial examples for automatically testing deep learning (DL) systems, such as image-based DL systems. However, the approaches contain the following two limitations. First, existing approaches only take into account small perturbations on adversarial examples, they design and generate adversarial examples for a certain particular DNN model. This might hamper the transferability of the examples for other DNN models. Second, they only use shallow features (e.g., pixel-level features) to judge the differences between the generated adversarial examples and the original examples. The deep features, which contain high-level semantic information, such as image object categories and scene semantics, are completely neglected. To address these two problems, we proposeCAGFuzz, aCoverage-guidedAdversarialGenerativeFuzzing testing approach for image-based DL systems.CAGFuzzis able to generate adversarial examples for mainstream DNN models to discover their potential errors. First, we train an Adversarial Example Generator (AEG) based on general datasets.AEGonly considers the data characteristics to alleviate the transferability problem. Second, we extract the deep features of the original and adversarial examples, and constrain the adversarial examples by cosine similarity to ensure that the deep features of the adversarial examples remain unchanged. Finally, we use the adversarial examples to retrain the models. Based on several standard datasets, we design a set of dedicated experiments to evaluateCAGFuzz. The experimental results show thatCAGFuzzcan detect more hidden errors, enhance the accuracy of the target DNN models, and generate adversarial examples with higher transferability.

At present, most smart contract vulnerability detection use manually-defined patterns, which is time-consuming and far from satisfactory. To address this issue, researchers attempt to deploy deep learning techniques for automatic vulnerability detection in smart contracts. Nevertheless, current work mostly relies on a single code representation such as AST (Abstract Syntax Tree) or code tokens to learn vulnerability characteristics, which might lead to incompleteness of learned semantics information. In addition, the number of available vulnerability datasets is also insufficient. To address these limitations, first, we construct a dataset covering most typical types of smart contract vulnerabilities, which can accurately indicate the specific row number where a vulnerability may exist. Second, for each single code representation, we propose a novel way called AFS (AST Fuse program Slicing) to fuse code characteristic information. AFS can fuse the structured information of AST with program slicing information and detect vulnerabilities by learning new vulnerability characteristic information.

Social sensing is a paradigm that allows crowd-sourcing data from humans and devices. This sensed data (e.g. social network posts) can be hosted in social-sensor clouds (i.e. social networks) and delivered as social-sensor cloud services (SocSen services). These services can be identified by their providers' social network accounts. Attackers intrude social-sensor clouds by cloning SocSen service providers' user profiles to deceive social-sensor cloud users. We propose a novel unsupervised SocSen service provider identity cloning detection approach, NPS-AntiClone, to prevent the detrimental outcomes caused by such identity deception. This approach leverages non-privacy-sensitive user profile data gathered from social networks to perform cloned identity detection. It consists of three main components: 1) a multi-view account representation model, 2) an embedding learning model and 3) a prediction model. The multi-view account representation model forms three different views for a given identity, namely a post view, a network view and a profile attribute view. The embedding learning model learns a single embedding from the generated multi-view representation using Weighted Generalized Canonical Correlation Analysis. Finally, NPS-AntiClone calculates the cosine similarity between two accounts' embedding to predict whether these two accounts contain a cloned account and its victim. We evaluated our proposed approach using a real-world dataset. The results showed that NPS-AntiClone significantly outperforms the existing state-of-the-art identity cloning detection techniques and machine learning approaches.

We propose a novel framework that detects conflicts in IoT-based smart homes. Conflicts may arise during interactions between the resident and IoT services in smart homes. We propose a generic knowledge graph to represent the relations between IoT services and environment entities. We also profile a generic knowledge graph to a specific smart home setting based on the context information. We propose a conflict taxonomy to capture different types of conflicts in a single resident smart home setting. A conflict detection algorithm is proposed to identify potential conflicts using the profiled knowledge graph. We conduct a set of experiments on real datasets and synthesized datasets to validate the effectiveness and efficiency of our proposed approach.

Mobile edge computing is a new computing paradigm that performs computing on the edge of a network. It provides services to users by deploying edge servers near mobile devices. Services may be unavailable or do not satisfy the needs of users due to changing edge environments. Quality of service (QoS) is commonly employed as a critical means to indicate qualitative status of services. It is particularly important to monitor QoS of services timely and effectively in the mobile edge environment. However, user mobility and dependencies among QoS values often cause the monitoring results to deviate from the real results in the mobile edge environment. Existing QoS monitoring approaches have not taken into account these problems. To address the problems, this article proposes ghBSRM-MEC (GaussianhiddenBayeSianRuntimeMonitoring forMobileEdgeComputing), a novel mobility and dependence-aware QoS monitoring approach for the mobile edge environment. This approach assumes that the QoS attribute values of edge servers obey Gaussian distribution. It constructs a parent property for each property, thus reducing the dependence between properties. During the training stage, a Gaussian Hidden Bayesian classifier is constructed for each edge server. During the monitoring stage, combining with a KNN algorithm, the classifier is changed dynamically based on user mobility to realize QoS monitoring in the mobile edge environment. The experimental results validate the feasibility, effectiveness, and efficiency of ghBSRM-MEC.

We propose aLong-term Quality of Service (QoS) forecasting approach usingAdvertisement andLevenberg-Marquardt improvedRadialBasisFunction (LA-LMRBF)—a novel online QoS forecasting approach. LA-LMRBF aims to accurately predict QoS attributes of Web services in the form of multivariate time series via three stages. First, the phase space reconstruction theory is employed to restore multi-dimensional and nonlinear relations among the multivariate QoS attributes. Second, short-term QoS advertisement data is incorporated to enable long-term QoS forecasting. Finally, an optimized Radial Basis Function (RBF) neural network is constructed to forecast long-term multivariate QoS values, where the Affinity Propagation clustering algorithm is used to determine the number of hidden nodes and the Levenberg-Marquardt (LM) algorithm is utilized to dynamically update some parameters of the RBF neural network. A series of experiments are performed on a mixture of public and self-collected data sets. The results show that LA-LMRBF is superior to the other approaches and more suitable for long-term QoS forecasting.

This paper proposes a novel security-aware QoS (Quality of Service) forecasting approach - Edge QoS Per-PM (Edge QoS forecasting with Personalized training based on Public Models in mobile edge computing) by migrating the principle of integrating cooperative learning and independent learning from federated learning. Edge QoS Per-PM can make fast and accurate forecasting on the premise of ensuring enhanced security. We train private model based on public model for personalized forecasting. The private models are invisible to other users to ensure the absolute security. At regular intervals, a Long Short-Term Memory (LSTM) model is trained based on the latest private data to meet the realtime requirements of the dynamic edge environment and ensure the accuracy of prediction results. A series of experiments is conducted based on public network data sets. The results demonstrate that Edge QoS Per-PM can train appropriate models and achieve faster convergence and higher accuracy.

Mobile edge computing transfers computing and storage from traditional cloud servers to edge servers, presenting new challenges to quality assurance of edge services. Quality of Service (QoS) is considered as a defacto standard to evaluate similar services with different quality. Given the fact that QoS values are highly dynamic in complex edge environments, QoS monitoring is viewed as a promising technique to comprehensively and effectively understand QoS status of edge services. Due to the distributed storage of historical QoS data and the changeable edge environments, traditional QoS monitoring approaches cannot be directly applied into mobile edge computing. To address this problem, this paper proposes a novel multivariate QoS monitoring approach, called Rs-mBSRM (multivariate BayeSian Runtime Monitoring using Rough set), First, the weights of different QoS attributes are quantified and obtained according to the historical samples based on rough set theory. Second, a Bayesian classifier is constructed for each corresponding edge server during the training stage. Finally, during the monitoring stage, considering the distributed data storage, the classifier is dynamically switched and the attribute weights are also updated due to user mobility. Our experimental results on public data sets show that Rs-mBSRM is better than existing QoS monitoring approaches and is more suitable for mobile edge computing.

Predictive analytics in Mobile Edge Computing (MEC) based Internet of Things (IoT) is becoming a high demand in many real-world applications. A prediction problem in an MEC-based IoT environment typically corresponds to a collection of tasks with each task solved in a specific MEC environment based on the data accumulated locally, which can be regarded as a Multi-task Learning (MTL) problem. However, the heterogeneity of the data (non-IIDness) accumulated across different MEC environments challenges the application of general MTL techniques in such a setting. Federated MTL (FMTL) has recently emerged as an attempt to address this issue. Besides FMTL, there exists another powerful but under-exploited distributed machine learning technique, called Network Lasso (NL), which is inherently related to FMTL but has its own unique features. In this paper, we made an in-depth evaluation and comparison of these two techniques on three distinct IoT datasets representing real-world application scenarios. Experimental results revealed that NL outperformed FMTL in MEC-based IoT environments in terms of both accuracy and computational efficiency.

We propose a distributed machine-learning architecture to predict trustworthiness of sensor services in Mobile Edge Computing (MEC) based Internet of Things (IoT) services, which aligns well with the goals of MEC and requirements of modern IoT systems. The proposed machine-learning architecture models training a distributed trust prediction model over a topology of MEC-environments as a Network Lasso problem, which allows simultaneous clustering and optimization on large-scale networked-graphs. We then attempt to solve it using Alternate Direction Method of Multipliers (ADMM) in a way that makes it suitable for MEC-based IoT systems. We present analytical and simulation results to show the validity and efficiency of the proposed solution.

We propose a new social-sensor cloud services trust model. We propose to represent social media data streams, i.e., images' meta-data and related posted information, as social-sensor cloud services. Images' meta-data and the related posted information are abstracted as the functional and non-functional aspects of the social-sensor cloud services. The trustworthiness of a social-sensor cloud service is measured based on the users' stance based trust model. We use the textual features of the social-sensor cloud services, i.e., comments and meta-data, e.g., spatio-temporal information to gather the trust-rate of the service. Analytical results are presented to show the performance of the proposed model with real datasets.

We propose a novel dynamic metaheuristic optimization approach to compose an optimal set of IaaS service requests to align with an IaaS provider's long-term economic expectation. This approach is designed for the context that the IaaS provisioning subjects to resource and QoS constraints. In addition, the IaaS service requests have the features of dynamic resource and QoS requirements and variable arrival times. A new economic model is proposed to evaluate the similarity between the provider's long-term economic expectation and a composition of service requests. The evaluation incorporates the factors of dynamic pricing and operation cost modeling of the service requests. An innovative hybrid genetic algorithm is proposed that incorporates the economic inter-dependency among the requests as a heuristic operator and performs repair operations in local solutions to meet the resource and QoS constraints. The proposed approach generates dynamic global solutions by updating the heuristic operator at regular intervals with the runtime behavior data of an existing service composition. Experimental results preliminarily prove the feasibility of the proposed approach.

We propose a new framework for social-sensor cloud services selection based on spatio-textual correlation between user's query and service. The proposed research defines a formal social-sensor cloud service model that abstracts the functional and non-functional aspects of social-sensor data on the cloud in terms of spatio-temporal, textual and quality of service parameters. Proposed framework is a 4-stage filtering algorithm, to select social-sensor cloud services based on user query and quality of service demands. 4-stage filtering is based on spatial correlation, textual correlation, visual features and quality of service parameters. Analytical results are presented to show the performance of the proposed approach.

We propose a 'Sentiment Analysis as a Service' (SAaaS) framework that abstracts sentiments from social information services, analyses and transforms into useful information. We propose a dynamic service composition mechanism for sentiment analysis based on the social information service classification. We also propose a new quality model to assess the quality of social information services. We use social media based public health surveillance as a motivating scenario. In particular, we focus on the spatio-temporal properties of social media users' sentiments to identify the locations of disease outbreaks. Experiments are conducted on the real-world datasets. Analytical results preliminarily show the performance of our proposed approach.

We investigate the use of subjective metrics in social media to evaluate cloud service performance in the market. We first examine the subjective factors that drive cloud consumers to/from purchasing cloud services. These include the ability to achieve greater scalability, security concerns, etc. according to several industry surveys. We then analyse the correlation between the consumers' perception on those factors and the cloud market revenue growth. This paper identifies the unique subjective metrics that are indicative of cloud service performance from the market perspective. The cloud consumers' perception is sourced from several particular social media using sentiment analysis techniques. We focus on consumers' perception on a leading cloud provider that holds the majority of the cloud market share. We find that subjective metrics are empirically proved to be applicable in evaluating the performance of cloud services in the market.

We propose a cloud service composition framework that selects the optimal composition based on an end user's long-term Quality of Service (QoS) requirements. In a typical cloud environment, existing solutions are not suitable when service providers fail to provide the long-term QoS provision advertisements. The proposed framework uses a new multivariate QoS analysis to predict the long-term QoS provisions from service providers' historical QoS data and short-term advertisements represented using Time Series. The quality of the QoS prediction is improved by incorporating QoS attributes' intra correlations into the multivariate analysis. To select the optimal service composition, the proposed framework uses QoS time series' inter correlations and performs a novel time series group similarity approach on the predicted QoS values. Experiments are conducted on real QoS dataset and results prove the efficiency of the proposed approach.

Internet of Things (IoT) represents a cyber-physical world where physical things are interconnected on the Web. This paper presents an architecture designed for Energy-efficient Inter-organizational wireless sensor data collection Framework (EnIF). Environmental monitoring and urban sensing are two major application scenarios in IoT. Different from the traditional sensor environments, environmental sensing in IoT may require battery-powered nodes to perform the sensing tasks. Such a requirement raises a critical challenge to ensure that sensor data gathering can be collected in a timely and energy-efficient manner. Although numerous energy-efficient approaches for IoT scenarios have been proposed, previous works assumed the entire network was managed by a single organization in which the network establishment and communication have been pre-configured. This assumption is inconsistent with the fact that IoT is established in a federated network with heterogeneous devices controlled by different organizations. The aim of the framework is to enable a dynamic inter-organizational collaborative topology towards saving energy from data transmissions using a service-oriented architecture.

We propose a novel composition framework for an Infrastructure-as-a-Service (IaaS) provider that selects the optimal set of long-term service requests to maximize its profit. Existing solutions consider an IaaS provider's economic benefits at the time of service composition and ignore the dynamic nature of the consumer requests in a long-term period. The proposed framework deploys a new multivariate HMM and ARIMA model to predict different patterns of resource utilization and Quality of Service fluctuation tolerance levels of existing service consumers. The dynamic nature of new consumer requests with no history is modelled using a new community based heuristic approach. The predicted long-term service requests are optimized using Integer Linear Programming to find a proper configuration that maximizes the profit of an IaaS provider. Experimental results prove the feasibility of the proposed approach.

With the advent of Cloud computing and subsequent big data, online decision makers usually find it difficult to make informed decisions because of the great amount of irrelevant, uncertain, or inaccurate information. In this paper, we explore the application of multicriteria decision-making (MCDM) techniques in the area of Cloud computing and big data, to find an efficient way of dealing with criteria relations and fuzzy knowledge based on a great deal of information. We propose a MCDM framework, which combines the ISM-based and ANP-based techniques, to model the interactive relations between evaluation criteria, and to handle data uncertainties. We present an application of Cloud service selection to prove the efficiency of the proposed framework, in which a user-oriented sigmoid utility function is designed to evaluate the performance of each criterion.

QoS-based service rating has made positive contributions to the area of service selection. Especially for Cloud service users, the right decision when choosing suitable Cloud services can help them improve user satisfaction and trading revenues. This work aims to address the issue of uncertainty in service requests, service descriptions, user and expert preferences, as well as evaluation criteria in a MCDM-based service selection procedure. A hybrid fuzzy framework for Cloud service selection is proposed, addressing the challenge using three approaches: a fuzzy-ontology-based approach for function matching and service filtering, a fuzzy AHP technique for informed criterion weighting, and, a fuzzy TOPSIS approach for service ranking.

It is well recognized that the Internet has become the largest marketplace in the world, and online advertising is very popular with numerous industries, including the traditional mining service industry where mining service advertisements are effective carriers of mining service information. However, service users may encounter three major issues – heterogeneity, ubiquity, and ambiguity, when searching for mining service information over the Internet. In this paper, we present the framework of a novel self-adaptive semantic focused crawler – SASF crawler, with the purpose of precisely and efficiently discovering, formatting, and indexing mining service information over the Internet, by taking into account the three major issues. This framework incorporates the technologies of semantic focused crawling and ontology learning, in order to maintain the performance of this crawler, regardless of the variety in the Web environment. The innovations of this research lie in the design of an unsupervised framework for vocabulary-based ontology learning, and a hybrid algorithm for matching semantically relevant concepts and metadata. A series of experiments are conducted in order to evaluate the performance of this crawler. The conclusion and the direction of future work are given in the final section.

Microblogging such as Twitter provides a rich source of information about products, personalities, and trends, etc. We proposed a simple methodology for analyzing sentiment of users in Twitter. First, we automatically collected Twitter corpus in positive and negative tweets. Second, we built a simple sentiment classifier by utilizing the Naive Bayes model to determine the positive and negative sentiment of a tweet. Third, we tested the classifier against a collection of users' opinions from five interesting domains of Twitter, i.e., news, finance, job, movies, and sport. The experimental results show that it is feasible to use Twitter corpus alone to classify new tweet for a certain domain applications.

SUMMARY The rapid increase in the volume of data available on the Internet makes it increasingly impractical for a crawler to index the whole Web. Instead, many intelligent crawlers, known as ontology‐based semantic focused crawlers, have been designed by making use of Semantic Web technologies for topic‐centered Web information crawling. Ontologies, however, have constraints of validity and time, which may influence the performance of the crawlers. Ontology‐learning‐based focused crawlers are therefore designed to automatically evolve ontologies by integrating ontology learning technologies. Nevertheless, surveys indicate that the existing ontology‐learning‐based focused crawlers do not have the capability to automatically enrich the content of ontologies, which makes these crawlers unreliable in the open and heterogeneous Web environment. Hence, in this paper, we propose a framework for a novel semi‐supervised ontology‐learning‐based focused (SOF) crawler, the SOF crawler, which embodies a series of schemas for ontology generation and Web information formatting, a semi‐supervised ontology learning framework, and a hybrid Web page classification approach aggregated by a group of support vector machine models. A series of tests are implemented to evaluate the technical feasibility of this proposed framework. The conclusion and the future work are summarized in the final section. Copyright © 2012 John Wiley & Sons, Ltd.

SUMMARY Web services provide a standard means for the interoperable operations between electronic devices in a network. The mission of Web service discovery is to seek an appropriate Web service for a service requester on the basis of the service descriptions in Web service advertisements and the service requester's requirements. Nevertheless, the standard language used for encoding service descriptions does not have the capacity to specify the capabilities of a Web service, leading to the problem of ambiguity in the service discovery process. This brings up the vision of Semantic Web Services and Semantic Web Service discovery, which make use of the Semantic Web technologies to enrich the semantics of service descriptions for service discovery. Semantic Web Service matchmakers are the programs or frameworks designed to implement the task of Semantic Web Service discovery and have drawn a significant amount of attention from both academia and industry from the start of this century. In this paper, we conduct a survey of the contemporary Semantic Web Service matchmakers in order to obtain an overview of the state of the art in this research area. We summarize six technical dimensions from the past literature and analyze the typical Semantic Web Service matchmakers mostly developed during the past 4 or 5 years in terms of the six dimensions. By means of this analysis, we gain an understanding of the current research and summarize a series of potential issues to that would provide the foundation for future research in this area.Copyright © 2012 John Wiley & Sons, Ltd.

Abstract While many researchers have contributed to the field of semantic similarity models so far, we find that most of the models are designed for the semantic network environment. When applying the semantic similarity model within the semantic‐rich ontology environment, two issues are observed: (1) most of the models ignore the context of ontology concepts and (2) most of the models ignore the context of relations. Therefore, in this paper, we present a solution for the two issues, including a novel ontology conversion process and a context‐aware semantic similarity model, by considering the factors of both the context of concepts and relations, and the ontology structure. Furthermore, in order to evaluate this model, we compare its performance with that of several existing models' performance in a large‐scale knowledge base, and the evaluation result preliminarily proves the technical advantage of our model in ontology environments. Conclusions and future works are described in the final section. Copyright © 2010 John Wiley & Sons, Ltd.

Digital Ecosystem is an innovative high-tech environment with the purpose of supporting the activities among species within the business ecosystem. In this paper, we concern about the research issue of service retrieval within such an environment. Due to the fact that species are heterogeneous and geographically dispersed, to precisely and quickly locate a service provider becomes an issue. In addition, the Digital Ecosystem environment urgently requires the structualization of service information and a set of unified QoS measurement for service ranking and evaluation. In order to unfold the issues in detail, we use the means of case study and literature survey. Eventually we formulate the research issues in this domain and provide a possible solution.

It is observed that there are few service evaluation and ranking methodologies currently available in the SOE. In this paper, we propose an innovative service evaluation and ranking strategy, based on the measurement of trustworthiness and reputation of services (or service providers'). CCCI Metrics originally proposed and developed by Chang et al [1] is used to measure the trustworthiness and reputation of e-services. Here we extend the application of CCCI Metrics to the field of service retrieval. A java-based search engine prototype is designed, with the purpose of implementing the trustworthiness and reputation-based service search, evaluation and ranking. Conclusions and future works are drawn in the final section.

Digital Ecosystems is a neoteric terminology and there are two major definitions about it ◻ respectively from Soluta.Net and from Digital Ecosystem and Business Intelligence Institute. In this paper, to solve the ambiguous problem in Digital Ecosystem's definitions and to help researchers better understand what it is, by means of ontology, we propose a conceptual model to completely illustrate the concepts in Digital Ecosystem. By introducing a new ontology notation system, we deliver the Digital Ecosystem Ontology, to well define the components and explain the relationships between these components. Finally we realize the ontology in Protégé-owl and conclude our future works in the field.

It is well-known that ontology is utilized as an effective methodology to share domain-specific knowledge in multidisciplinary fields. In the field of project management, due to the characteristic of project organizations in which project members are geographically dispersed and from different cultural background, senior management would feel difficulty when they attempt to know about the detailed project completion status from dispersed project groups. Thus, the objective of this paper is to propose an automated project track and trace methodology through the use of ontology technology, to challenge the knowledge sharing issues in project organizations. By means of extending CCCI metrics into the field of project management and introducing a new ontological notation system, we deliver the project track and trace ontology.