Showing papers in "IEEE open journal of the Computer Society in 2023"
TL;DR: Wang et al. as mentioned in this paper proposed a blockchain-aided semantic communication framework for AIGC services in virtual transportation networks to facilitate interactions of the physical and virtual domains among VSPs and edge devices.
Abstract: The construction of virtual transportation networks requires massive data to be transmitted from edge devices to Virtual Service Providers (VSP) to facilitate circulations between the physical and virtual domains in Metaverse. Leveraging semantic communication for reducing information redundancy, VSPs can receive semantic data from edge devices to provide varied services through advanced techniques, e.g., AI-Generated Content (AIGC), for users to explore digital worlds. But the use of semantic communication raises a security issue because attackers could send malicious semantic data with similar semantic information but different desired content to break Metaverse services and cause wrong output of AIGC. Therefore, in this paper, we first propose a blockchain-aided semantic communication framework for AIGC services in virtual transportation networks to facilitate interactions of the physical and virtual domains among VSPs and edge devices. We illustrate a training-based targeted semantic attack scheme to generate adversarial semantic data by various loss functions. We also design a semantic defense scheme that uses the blockchain and zero-knowledge proofs to tell the difference between the semantic similarities of adversarial and authentic semantic data and to check the authenticity of semantic data transformations. Simulation results show that the proposed defense method can reduce the semantic similarity of the adversarial semantic data and the authentic ones by up to 30% compared with the attack scheme.
8 citations
DOI•
TL;DR: In this paper , the authors present a formal definition of particle methods and demonstrate its importance by applying it to various canonical and non-canonical algorithms, using it to prove a theorem about multi-core parallelizability, and designing a principled scientific computing software based on it.
Abstract: Particle methods are a widely used class of algorithms for computer simulation of complex phenomena in various fields, such as fluid dynamics, plasma physics, molecular chemistry, and granular flows, using diverse simulation methods, including Smoothed Particle Hydrodynamics (SPH), Particle-in-Cell (PIC) methods, Molecular Dynamics (MD), and Discrete Element Methods (DEM). Despite the increasing use of particle methods driven by improved computing performance, the relation between these algorithms remains formally unclear, and a unifying formal definition of particle methods is lacking. Here, we present a rigorous mathematical definition of particle methods and demonstrate its importance by applying it to various canonical and non-canonical algorithms, using it to prove a theorem about multi-core parallelizability, and designing a principled scientific computing software based on it. We anticipate that our formal definition will facilitate the solution of complex computational problems and the implementation of understandable and maintainable software frameworks for computer simulation.
3 citations
TL;DR: In this paper , the authors provide a comprehensive overview and taxonomy of the security risks and financial crimes that have emerged since the development of the decentralized metaverse, focusing on three issues: existing definitions, relevant cases and analysis, and existing academic research on this type of crime.
Abstract: At present, the concept of metaverse has sparked widespread attention from the public to major industries. With the rapid development of blockchain and Web3 technologies, the decentralized metaverse ecology has attracted a large influx of users and capital. Due to the lack of industry standards and regulatory rules, the Web3-empowered metaverse ecosystem has witnessed a variety of financial crimes, such as scams, code exploit, wash trading, money laundering, and illegal services and shops. To this end, it is especially urgent and critical to summarize and classify the financial security threats on the Web3-empowered metaverse in order to maintain the long-term healthy development of its ecology. In this paper, we first outline the background, foundation, and applications of the Web3 metaverse. Then, we provide a comprehensive overview and taxonomy of the security risks and financial crimes that have emerged since the development of the decentralized metaverse. For each financial crime, we focus on three issues: a) existing definitions, b) relevant cases and analysis, and c) existing academic research on this type of crime. Next, from the perspective of academic research and government policy, we summarize the current anti-crime measurements and technologies in the metaverse. Finally, we discuss the opportunities and challenges in behavioral mining and the potential regulation of financial activities in the metaverse. The overview of this paper is expected to help readers better understand the potential security threats in this emerging ecology, and to provide insights and references for financial crime fighting.
3 citations
TL;DR: Wang et al. as mentioned in this paper proposed a blockchain-aided semantic communication framework for AIGC services in virtual transportation networks to facilitate interactions of the physical and virtual domains among VSPs and edge devices.
Abstract: The construction of virtual transportation networks requires massive data to be transmitted from edge devices to Virtual Service Providers (VSP) to facilitate circulations between the physical and virtual domains in Metaverse. Leveraging semantic communication for reducing information redundancy, VSPs can receive semantic data from edge devices to provide varied services through advanced techniques, e.g., AI-Generated Content (AIGC), for users to explore digital worlds. But the use of semantic communication raises a security issue because attackers could send malicious semantic data with similar semantic information but different desired content to break Metaverse services and cause wrong output of AIGC. Therefore, in this paper, we first propose a blockchain-aided semantic communication framework for AIGC services in virtual transportation networks to facilitate interactions of the physical and virtual domains among VSPs and edge devices. We illustrate a training-based targeted semantic attack scheme to generate adversarial semantic data by various loss functions. We also design a semantic defense scheme that uses the blockchain and zero-knowledge proofs to tell the difference between the semantic similarities of adversarial and authentic semantic data and to check the authenticity of semantic data transformations. Simulation results show that the proposed defense method can reduce the semantic similarity of the adversarial semantic data and the authentic ones by up to 30% compared with the attack scheme.
2 citations
DOI•
TL;DR: Wang et al. as discussed by the authors designed a decentralized identity (DID) protocol to solve the single point of failure and privacy data leakage in online social networks, which includes a range proof protocol to provide attribute privacy.
Abstract: Online social networks (OSNs) are becoming more and more popular in people's lives as the demand for online interaction continues to grow. Current OSNs are using centralized identity management system (IDM), which has some problems of single point of failure and privacy data leakage. The emergence of decentralized identity (DID) can solve these problems. However, most existing DID systems have some privacy issues that a user's attributes value are disclosed while accessing service. In this paper, we design a DID protocol to solve these challenges. The proposed protocol includes a range proof protocol to provide attribute privacy. The range proof protocol works with anonymous credentials and does not need a trusted setup. Moreover, the identity model behind the DID protocol is extended from an existing model, which achieves identity revocation. Finally, we implement a system prototype on the blockchain for evaluation. The security analysis shows that our protocol provides stronger privacy protection. The performance evaluation indicates that the computation cost and blockchain overheads of our protocol are acceptable in OSNs.
1 citations
TL;DR: Wang et al. as mentioned in this paper designed a decentralized identity (DID) protocol to solve the single point of failure and privacy data leakage in online social networks, which includes a range proof protocol to provide attribute privacy.
Abstract: Online social networks (OSNs) are becoming more and more popular in people's lives as the demand for online interaction continues to grow. Current OSNs are using centralized identity management system (IDM), which has some problems of single point of failure and privacy data leakage. The emergence of decentralized identity (DID) can solve these problems. However, most existing DID systems have some privacy issues that a user's attributes value are disclosed while accessing service. In this paper, we design a DID protocol to solve these challenges. The proposed protocol includes a range proof protocol to provide attribute privacy. The range proof protocol works with anonymous credentials and does not need a trusted setup. Moreover, the identity model behind the DID protocol is extended from an existing model, which achieves identity revocation. Finally, we implement a system prototype on the blockchain for evaluation. The security analysis shows that our protocol provides stronger privacy protection. The performance evaluation indicates that the computation cost and blockchain overheads of our protocol are acceptable in OSNs.
1 citations
TL;DR: In this paper , the authors focus on the communication, validation platform, and simulator of multi-robot systems, and discuss one of the important applications, cooperative object transport in real-world applications.
Abstract: Multi-robot systems gain considerable attention due to lower cost, better robustness, and higher scalability as compared with single-robot systems. Cooperative object transport, as a well-known use case of multi-robot systems, shows great potential in real-world applications. The design and implementation of a multi-robot system involve many technologies, specifically, communication, coordination, task allocation methods, experimental platforms, and simulators. However, most of recent multi-robot system studies focus on coordination and task allocation problems, with little focus on communications among multiple robots. In this review, we focus on the communication, validation platform, and simulator of multi-robot systems, and discuss one of the important applications, cooperative object transport. First, we study the multi-robot system fundamentals and comprehensively review the multi-robot system communication technologies. Then, the multi-robot system validating platform, testbed, simulator, and middleware used in academia and industry are investigated. Finally, we discuss recent advances in cooperative object transport, and challenges and possible future research directions for multi-robot systems.
1 citations
TL;DR: In this article , the authors provide a comprehensive overview of blockchain-based decentralized applications (DApp) for further research and provide an overview of the recent research problems of DApps from the perspectives of economics, security, and performance.
Abstract: Blockchain-based decentralized applications (DApp) draw more attention with the increasing development and wide application of blockchain technologies. A wealth of funds are invested into the crowd-funding of various types of DApp. As reported in August 2022, there are more than 5,000 DApps with more than 1.67 million daily Unique Active Wallets (users). However, the definition, architectures, and classifications of the DApps are still not cleared up till now. This survey aims to provide a comprehensive overview of DApps for further research. First, the definitions and typical architectures of DApps are presented. Then we collect 3,118 popular DApps and categorize them into different types, and summarize their typical advantages and challenges. Finally, we provide an overview of the recent research problems of DApps from the perspectives of economics, security, and performance and then figure out promising research opportunities in the future.
1 citations
TL;DR: In this paper , the authors provide a comprehensive overview of blockchain-based decentralized applications (DApp) for further research and provide an overview of the recent research problems of DApps from the perspectives of economics, security, and performance.
Abstract: Blockchain-based decentralized applications (DApp) draw more attention with the increasing development and wide application of blockchain technologies. A wealth of funds are invested into the crowd-funding of various types of DApp. As reported in August 2022, there are more than 5,000 DApps with more than 1.67 million daily Unique Active Wallets (users). However, the definition, architectures, and classifications of the DApps are still not cleared up till now. This survey aims to provide a comprehensive overview of DApps for further research. First, the definitions and typical architectures of DApps are presented. Then we collect 3,118 popular DApps and categorize them into different types, and summarize their typical advantages and challenges. Finally, we provide an overview of the recent research problems of DApps from the perspectives of economics, security, and performance and then figure out promising research opportunities in the future.
1 citations
TL;DR: Wang et al. as mentioned in this paper proposed a light-weight GPS spoofing detection method based on a dynamic threshold and captured signal envelope, which revealed the relation between envelope characteristics and the distance between a GPS transmitter and receiver.
Abstract: Global Positioning System (GPS) spoofing attacks have attracted more attention as one of the most effective GPS attacks. Since the signals from an authentic satellite and the spoofer undergo different attenuation, the captured envelope of fake GPS signals exhibits distinctive transmission characteristics due to short transmission paths. This can be utilized for GPS spoofing detection. The existing technique for GPS spoofing are either computationally too expensive, require specialize hardware/software updates, or are not accurate enough. To solve these issues, we propose a light-weight GPS spoofing detection method based on a dynamic threshold and captured signal envelope. We validate the proposed technique using experiments based on actual GPS signals and hardware. The relation between envelope characteristics and the distance between a GPS transmitter and receiver are revealed. Inspired by the uncovered relation, a threshold approach towards the detection of GPS spoofing is developed. The proposed approach features a dynamic threshold determined by the dispersion value of a signal envelope's variance instead of a fixed threshold to maximize detection performance in multiple attack scenarios. The results show that the proposed technique can effectively detect GPS spoofing attacks with better accuracy and lower computational complexity as compared to existing techniques.
1 citations
TL;DR: In this paper , a light-weight GPS spoofing detection method based on a dynamic threshold and captured signal envelope is proposed, where the relation between envelope characteristics and the distance between a GPS transmitter and receiver is revealed.
Abstract: Global Positioning System (GPS) spoofing attacks have attracted more attention as one of the most effective GPS attacks. Since the signals from an authentic satellite and the spoofer undergo different attenuation, the captured envelope of fake GPS signals exhibits distinctive transmission characteristics due to short transmission paths. This can be utilized for GPS spoofing detection. The existing technique for GPS spoofing are either computationally too expensive, require specialize hardware/software updates, or are not accurate enough. To solve these issues, we propose a light-weight GPS spoofing detection method based on a dynamic threshold and captured signal envelope. We validate the proposed technique using experiments based on actual GPS signals and hardware. The relation between envelope characteristics and the distance between a GPS transmitter and receiver are revealed. Inspired by the uncovered relation, a threshold approach towards the detection of GPS spoofing is developed. The proposed approach features a dynamic threshold determined by the dispersion value of a signal envelope's variance instead of a fixed threshold to maximize detection performance in multiple attack scenarios. The results show that the proposed technique can effectively detect GPS spoofing attacks with better accuracy and lower computational complexity as compared to existing techniques.
TL;DR: In this article , the authors focus on the communication, validation platform, and simulator of multi-robot systems, and discuss one of the important applications, cooperative object transport in real-world applications.
Abstract: Multi-robot systems gain considerable attention due to lower cost, better robustness, and higher scalability as compared with single-robot systems. Cooperative object transport, as a well-known use case of multi-robot systems, shows great potential in real-world applications. The design and implementation of a multi-robot system involve many technologies, specifically, communication, coordination, task allocation methods, experimental platforms, and simulators. However, most of recent multi-robot system studies focus on coordination and task allocation problems, with little focus on communications among multiple robots. In this review, we focus on the communication, validation platform, and simulator of multi-robot systems, and discuss one of the important applications, cooperative object transport. First, we study the multi-robot system fundamentals and comprehensively review the multi-robot system communication technologies. Then, the multi-robot system validating platform, testbed, simulator, and middleware used in academia and industry are investigated. Finally, we discuss recent advances in cooperative object transport, and challenges and possible future research directions for multi-robot systems.
TL;DR: In this paper , the authors proposed a new algorithm called FLIS that aims to address this problem by grouping clients into clusters that have jointly trainable data distributions by comparing the data distribution of client models.
Abstract: Conventional federated learning (FL) approaches are ineffective in scenarios where clients have significant differences in the distributions of their local data. The Non-IID data distribution in the client data causes a drift in the local model updates from the global optima, which significantly impacts the performance of the trained models. In this paper, we present a new algorithm called FLIS that aims to address this problem by grouping clients into clusters that have jointly trainable data distributions. This is achieved by comparing the inference similarity of client models. Our proposed framework captures settings where different groups of users may have their own objectives (learning tasks), but by aggregating their data with others in the same cluster (same learning task), superior models can be derived via more efficient and personalized federated learning. We present experimental results to demonstrate the benefits of FLIS over the state-of-the-art approaches on the CIFAR-100/10, SVHN, and FMNIST datasets. Our code is available at https://github.com/MMorafah/FLIS .
TL;DR: In this article , the authors proposed an algorithm that uses two different masks for processing two different types of object voxels, i.e., one mask is used when the voxel preceding the object being processed is an object and the other one is used otherwise.
Abstract: Conventional voxel-based algorithms for labeling connected components in 3D binary images use the same mask to process all object voxels. To reduce the number of times that neighboring voxels are checked when object voxels are processed, we propose an algorithm that uses two different masks for processing two different types of object voxels. One type of mask is used when the voxel preceding the object voxel being processed is an object voxel, and the other type is used otherwise. In either case, an optimal order is used for checking the voxels in the corresponding mask. Experimental results demonstrate that our proposed algorithm checked fewer voxels, and was more efficient than conventional algorithms.
TL;DR: In this paper , a generic design methodology to achieve area-efficient reconfigurable logic circuits by using exact synthesis based on Boolean satisfiability (SAT) solver is proposed, which better leverages the high representation ability of emerging reconfigable logic gates (RLGs) to achieve fewer gates.
Abstract: In this paper, we propose a generic design methodology to achieve area-efficient reconfigurable logic circuits by using exact synthesis based on Boolean satisfiability (SAT) solver. The proposed methodology better leverages the high representation ability of emerging reconfigurable logic gates (RLGs) to achieve reconfigurable circuits with fewer gates. In addition, we propose a fence-based acceleration method to provide >10× speed up for the synthesis without an observable loss of optimality. Furthermore, four sets of RLGs are developed based on a recently proposed valley-spin device as a case study to demonstrate the advantage of the proposed circuit. Simulations have been performed to analyze the impact of the fence searching algorithm and combination of operators. Based on disjoint-support decomposable (DSD) benchmarks, up to 38% and 73% reductions are observed in the area and energy-delay-area product (EDAP), respectively, compared to CMOS counterparts. Compared to the two existing synthesis methods, the proposed scheme provides 40% and 26.3% reduction in EDAP based on MCNC benchmark.
TL;DR: In this paper , the authors propose to infer a simple three-layer neural network with threshold activations, which can be trained using state-of-the-art training methods to achieve high prediction accuracy.
Abstract: While neural networks have been achieving increasingly significant excitement in solving classification tasks such as natural language processing, their lack of interpretability becomes a great challenge for neural networks to be deployed in certain high-stakes human-centered applications. To address this issue, we propose a new approach for generating interpretable predictions by inferring a simple three-layer neural network with threshold activations, so that it can benefit from effective neural network training algorithms and at the same time, produce human-understandable explanations for the results. In particular, the hidden layer neurons in the proposed model are trained with floating point weights and binary output activations. The output neuron is also trainable as a threshold logic function that implements a disjunctive operation, forming the logical-OR of the first-level threshold logic functions. This neural network can be trained using state-of-the-art training methods to achieve high prediction accuracy. An important feature of the proposed architecture is that only a simple greedy algorithm is required to provide an explanation with the prediction that is human-understandable. In comparison with other explainable decision models, our proposed approach achieves more accurate predictions on a broad set of tabular data classification datasets.
TL;DR: Wang et al. as discussed by the authors proposed an incentive mechanism that utilizes contract-theoretic methods to economically motivate users to support the sustainability and growth of the blockchain network, which addresses the problem of information asymmetry (e.g., users' revenue-generating capabilities and efforts) between users and blockchain network.
Abstract: This article explores the role of blockchains in the development of Web 3.0 and the Metaverse. The success of these technologies is dependent on the utilization of decentralized systems like blockchains, which can store and validate data on identities and reputations and facilitate the exchange of virtual assets. Full nodes, which store the entire blockchain state and validate all transactions, are essential for the decentralization and reliability of the network. However, operating a full node is resource-intensive and can be expensive. To tackle this challenge, we propose an incentive mechanism that utilizes contract-theoretic methods to economically motivate users to support the sustainability and growth of the blockchain network. Our contract design addresses the problem of information asymmetry (e.g., users' revenue-generating capabilities and efforts) between users and the blockchain network. Additionally, we recommend providing diverse incentives based on the user's revenue-generating capabilities and efforts to assist the blockchain network in funding incentives. Our experimental results demonstrate that our proposed mechanism increases the blockchain network's utility by $48.48\%-54.52\%$ and reduces the users' cost by $38.46\%-62.5\%$ compared with the state-of-the-art implementations such as Celo, Vipnode, and Pocket Network.
TL;DR: An intelligent Internet-of-Things (IoT) hardware system in the field tea plantations was built, comprising collection of tea images by HD zoom cameras in a cluster structure and deployment of the detection model by cluster-head edge computing nodes as mentioned in this paper .
Abstract: An intelligent Internet-of-Things (IoT) hardware system in the field tea plantations was built, comprising collection of tea images by HD zoom cameras in a cluster structure and deployment of the detection model by cluster-head edge computing nodes. Data was sent to customer premise equipment through edge nodes and gateways and then to cloud platforms, which provided a hardware platform for identifying remote tea disease online. Field-placed cameras were used as the main acquisition means to study various diseases on Yashixiang, a typical variety of Chaozhou Dancong tea, in different seasons and weather conditions and shooting angles in a natural year period with complex backgrounds. In turn, we constructed a natural environment high-quality dataset covering major diseases e.g., tea anthracnose, tea leaf blight, tea grey blight, Pseudocercospora theae, etc. and explored the feasibility of deep learning algorithms for automatic identification of Chaozhou Dancong tea diseases. Results showed that the recognition rate of Swim Transformer reached 94% in complex natural environments. This paper demonstrated the effectiveness of the dataset and the feasibility of deep learning algorithms applied to the automatic identification of diseases of Chaozhou Dancong tea, laying a foundation for the practical application of the technology in complex natural environments.
TL;DR: Wang et al. as mentioned in this paper proposed an incentive mechanism that utilizes contract-theoretic methods to economically motivate users to support the sustainability and growth of the blockchain network, which addresses the problem of information asymmetry (e.g., users' revenue-generating capabilities and efforts) between users and blockchain network.
Abstract: This paper explores the role of blockchains in the development of Web 3.0 and the Metaverse. The success of these technologies is dependent on the utilization of decentralized systems like blockchains, which can store and validate data on identities and reputations and facilitate the exchange of virtual assets. Full nodes, which store the entire blockchain state and validate all transactions, are essential for the decentralization and reliability of the network. However, operating a full node is resource-intensive and can be expensive. To tackle this challenge, we propose an incentive mechanism that utilizes contract-theoretic methods to economically motivate users to support the sustainability and growth of the blockchain network. Our contract design addresses the problem of information asymmetry (e.g., users' revenue-generating capabilities and efforts) between users and the blockchain network. Additionally, we recommend providing diverse incentives based on the user's revenue-generating capabilities and efforts to assist the blockchain network in funding incentives. Our experimental results demonstrate that our proposed mechanism increases the blockchain network's utility by $48.48\%-54.52\%$ $38.46\%-62.5\%$
TL;DR: In this article , a generic design methodology to achieve area-efficient reconfigurable logic circuits by using exact synthesis based on Boolean satisfiability (SAT) solver is proposed, which better leverages the high representation ability of emerging reconfigable logic gates (RLGs) to achieve fewer gates.
Abstract: In this article, we propose a generic design methodology to achieve area-efficient reconfigurable logic circuits by using exact synthesis based on Boolean satisfiability (SAT) solver. The proposed methodology better leverages the high representation ability of emerging reconfigurable logic gates (RLGs) to achieve reconfigurable circuits with fewer gates. In addition, we propose a fence-based acceleration method to provide >10× speed up for the synthesis without an observable loss of optimality. Furthermore, four sets of RLGs are developed based on a recently proposed valley-spin device as a case study to demonstrate the advantage of the proposed circuit. Simulations have been performed to analyze the impact of the fence searching algorithm and combination of operators. Based on disjoint-support decomposable (DSD) benchmarks, up to 38% and 73% reductions are observed in the area and energy-delay-area product (EDAP), respectively, compared to CMOS counterparts. Compared to the two existing synthesis methods, the proposed scheme provides 40% and 26.3% reduction in EDAP based on MCNC benchmark.
TL;DR: In this paper , a formal mathematical definition of particle methods is presented and applied to various canonical and non-canonical algorithms, using it to prove a theorem about multi-core parallelizability and designing a principled scientific computing software based on it.
Abstract: Particle methods are a widely used class of algorithms for computer simulation of complex phenomena in various fields, such as fluid dynamics, plasma physics, molecular chemistry, and granular flows, using diverse simulation methods, including Smoothed Particle Hydrodynamics (SPH), Particle-in-Cell (PIC) methods, Molecular Dynamics (MD), and Discrete Element Methods (DEM). Despite the increasing use of particle methods driven by improved computing performance, the relation between these algorithms remains formally unclear, and a unifying formal definition of particle methods is lacking. Here, we present a rigorous mathematical definition of particle methods and demonstrate its importance by applying it to various canonical and non-canonical algorithms, using it to prove a theorem about multi-core parallelizability, and designing a principled scientific computing software based on it. We anticipate that our formal definition will facilitate the solution of complex computational problems and the implementation of understandable and maintainable software frameworks for computer simulation.
TL;DR: In this paper , the authors propose to infer a simple three-layer neural network with threshold activations to generate human-understandable explanations for the results, which can be trained using state-of-the-art training methods to achieve high prediction accuracy.
Abstract: While neural networks have been achieving increasingly significant excitement in solving classification tasks such as natural language processing, their lack of interpretability becomes a great challenge for neural networks to be deployed in certain high-stakes human-centered applications. To address this issue, we propose a new approach for generating interpretable predictions by inferring a simple three-layer neural network with threshold activations, so that it can benefit from effective neural network training algorithms and at the same time, produce human-understandable explanations for the results. In particular, the hidden layer neurons in the proposed model are trained with floating point weights and binary output activations. The output neuron is also trainable as a threshold logic function that implements a disjunctive operation, forming the logical-OR of the first-level threshold logic functions. This neural network can be trained using state-of-the-art training methods to achieve high prediction accuracy. An important feature of the proposed architecture is that only a simple greedy algorithm is required to provide an explanation with the prediction that is human-understandable. In comparison with other explainable decision models, our proposed approach achieves more accurate predictions on a broad set of tabular data classification datasets.
TL;DR: In this paper , a reverse self-distillation method is proposed to improve the efficiency of self-learning by integrating the roles of teacher and student into a single network to solve the knowledge distillation problem.
Abstract: Deep neural networks generally cannot gather more helpful information with limited data in image classification, resulting in poor performance. Self-distillation, as a novel knowledge distillation technique, integrates the roles of teacher and student into a single network to solve this problem. A better understanding of the efficiency of self-distillation is critical to its advancement. In this article, we provide a new perspective: the effectiveness of self-distillation comes not only from distillation but also from the supervisory information provided by the shallow networks. At the same time, we find a barrier that limits the effectiveness of self-distillation. Based on this, reverse self-distillation is proposed. In contrast to self-distillation, the internal knowledge flow is in the opposite direction. Experimental results show that reverse self-distillation can break the barrier of self-distillation and further improve the accuracy of networks. On average, 2.8% and 3.2% accuracy boosts are observed on CIFAR100 and TinyImageNet.
TL;DR: An intelligent Internet-of-Things (IoT) hardware system in the field tea plantations was built, comprising collection of tea images by HD zoom cameras in a cluster structure and deployment of the detection model by cluster-head edge computing nodes as discussed by the authors .
Abstract: An intelligent Internet-of-Things (IoT) hardware system in the field tea plantations was built, comprising collection of tea images by HD zoom cameras in a cluster structure and deployment of the detection model by cluster-head edge computing nodes. Data was sent to customer premise equipment through edge nodes and gateways and then to cloud platforms, which provided a hardware platform for identifying remote tea disease online. Field-placed cameras were used as the main acquisition means to study various diseases on Yashixiang, a typical variety of Chaozhou Dancong tea, in different seasons and weather conditions and shooting angles in a natural year period with complex backgrounds. In turn, we constructed a natural environment high-quality dataset covering major diseases e.g., tea anthracnose, tea leaf blight, tea grey blight, Pseudocercospora theae, etc. and explored the feasibility of deep learning algorithms for automatic identification of Chaozhou Dancong tea diseases. Results showed that the recognition rate of Swim Transformer reached 94% in complex natural environments. This paper demonstrated the effectiveness of the dataset and the feasibility of deep learning algorithms applied to the automatic identification of diseases of Chaozhou Dancong tea, laying a foundation for the practical application of the technology in complex natural environments.
TL;DR: In this article , a reverse self-distillation method is proposed to improve the efficiency of self-learning by integrating the roles of teacher and student into a single network to solve the knowledge distillation problem.
Abstract: Deep neural networks generally cannot gather more helpful information with limited data in image classification, resulting in poor performance. Self-distillation, as a novel knowledge distillation technique, integrates the roles of teacher and student into a single network to solve this problem. A better understanding of the efficiency of self-distillation is critical to its advancement. In this paper, we provide a new perspective: the effectiveness of self-distillation comes not only from distillation but also from the supervisory information provided by the shallow networks. At the same time, we find a barrier that limits the effectiveness of self-distillation. Based on this, reverse self-distillation is proposed. In contrast to self-distillation, the internal knowledge flow is in the opposite direction. Experimental results show that reverse self-distillation can break the barrier of self-distillation and further improve the accuracy of networks. On average, 2.8% and 3.2% accuracy boosts are observed on CIFAR100 and TinyImageNet.
TL;DR: Li et al. as mentioned in this paper proposed a federated graph contrastive learning framework, which is able to update node embeddings during training by means of a federation method, allowing the local GCL to acquire anchors with richer information.
Abstract: As a self-supervised learning method, the graph contrastive learning achieve admirable performance in graph pre-training tasks, and can be fine-tuned for multiple downstream tasks such as protein structure prediction, social recommendation, etc. One prerequisite for graph contrastive learning is the support of huge graphs in the training procedure. However, the graph data nowadays are distributed in various devices and hold by different owners, like those smart devices in Internet of Things. Considering the non-negligible consumptions on computing, storage, communication, data privacy and other issues, these devices often prefer to keep data locally, which significantly reduces the graph contrastive learning performance. In this paper, we propose a novel federal graph contrastive learning framework. First, it is able to update node embeddings during training by means of a federation method, allowing the local GCL to acquire anchors with richer information. Second, we design a Self-adaptive Cluster-based server strategy to select the optimal embedding update scheme, which maximizes the richness of the embedding information while avoiding the interference of noise. Generally, our method can build anchors with richer information through a federated learning approach, thus alleviating the performance degradation of graph contrastive learning due to distributed storage. Extensive analysis and experimental results demonstrate the superiority of our framework.
TL;DR: In this paper , the authors introduce a mitigation technique called synchronous firing, where graph users and designers can prevent the generation of infeasible states by firing exploits simultaneously through joining inseparable features like time.
Abstract: Attack and compliance graphs are useful tools for cybersecurity and regulatory or compliance analysis. Thgraphs represent the state of a system or a set of systems, and can be used to identify all current or future ways the systems are compromised or at risk of violating regulatory or compliance mandates. However, due to their exhaustiveness and thorough permutation checking, these graphs suffer from state space explosion - the graphs rapidly increase in the total number of states, and likewise, their generation time also rapidly increases. This state space explosion in turn also slows the analysis process. This work introduces a mitigation technique called synchronous firing, where graph users and designers can prevent the generation of infeasible states by firing exploits simultaneously through joining inseparable features like time. This feature does not invalidate the integrity of the resulting attack or compliance graph by altering the exhaustiveness or permutation checking of the generation process, but rather jointly fires exploits through their defined inseparable features.
TL;DR: In this article , the authors introduce a mitigation technique called synchronous firing, where graph users and designers can prevent the generation of infeasible states by firing exploits simultaneously through joining inseparable features like time.
Abstract: Attack and compliance graphs are useful tools for cybersecurity and regulatory or compliance analysis. Thgraphs represent the state of a system or a set of systems, and can be used to identify all current or future ways the systems are compromised or at risk of violating regulatory or compliance mandates. However, due to their exhaustiveness and thorough permutation checking, these graphs suffer from state space explosion - the graphs rapidly increase in the total number of states, and likewise, their generation time also rapidly increases. This state space explosion in turn also slows the analysis process. This work introduces a mitigation technique called synchronous firing, where graph users and designers can prevent the generation of infeasible states by firing exploits simultaneously through joining inseparable features like time. This feature does not invalidate the integrity of the resulting attack or compliance graph by altering the exhaustiveness or permutation checking of the generation process, but rather jointly fires exploits through their defined inseparable features.