Pub Date : 2024-09-12DOI: 10.1109/TNSE.2024.3458095
Kaiyu Wang;Dan Ye
This paper proposes a data-driven complete stealthy attack strategy against cyber-physical systems (CPSs) based on the geometric approach. The attacker aims to degrade estimation performance and maintain stealthiness by compromising partial communication links of the actuator and sensor. Different from the classic analysis methods that require accurate model parameters, we focus on how to establish the connection between geometry and data-driven approaches to represent the malicious behavior of attacks on state estimation. First of all, the existence of complete stealthy attacks is analyzed. Then, the maximal attached stealthy subspace and the set of estimation errors under complete stealthy attacks are analyzed intuitively from the geometric point of view. On this basis, the complete stealthy subspace is constructed with the subspace identification method, which is applied to generate the corresponding stealthy attack sequence through the collected system input-output data. Finally, simulation results are provided to illustrate the effectiveness of the proposed strategies.
{"title":"Geometry-Based Data-Driven Complete Stealthy Attacks Against Cyber-Physical Systems","authors":"Kaiyu Wang;Dan Ye","doi":"10.1109/TNSE.2024.3458095","DOIUrl":"10.1109/TNSE.2024.3458095","url":null,"abstract":"This paper proposes a data-driven complete stealthy attack strategy against cyber-physical systems (CPSs) based on the geometric approach. The attacker aims to degrade estimation performance and maintain stealthiness by compromising partial communication links of the actuator and sensor. Different from the classic analysis methods that require accurate model parameters, we focus on how to establish the connection between geometry and data-driven approaches to represent the malicious behavior of attacks on state estimation. First of all, the existence of complete stealthy attacks is analyzed. Then, the maximal attached stealthy subspace and the set of estimation errors under complete stealthy attacks are analyzed intuitively from the geometric point of view. On this basis, the complete stealthy subspace is constructed with the subspace identification method, which is applied to generate the corresponding stealthy attack sequence through the collected system input-output data. Finally, simulation results are provided to illustrate the effectiveness of the proposed strategies.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"5839-5849"},"PeriodicalIF":6.7,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recent studies have demonstrated that deep neural networks show excellent performance in information hiding. Considering the tremendous progress that deep learning has made in image recognition, we explore whether neural networks can recognize invisible private images hidden in cover images. In this article, we propose a method for image recognition in the covert domain using neural networks. Our target is to hide an image inside another image with minimal visual quality loss, while at the same time, the hidden image can be recognized correctly without being recovered. In the proposed system, the hiding and recognition of secret images are all performed by neural networks. The hiding network and the recognition network are designed to specifically work as a pair. We design and jointly train preparation, hiding, and recognition networks, where given a cover and a secret image, the preparation network reduces redundant information of the secret image, the hiding network produces a stego image that is visually indistinguishable from the cover image, and the PSNR and SSIM reach 38.5 dB and 0.991 on the MNIST & CIFAR-10 dataset and 41.8 dB and 0.995 on the CelebA & Scene dataset, respectively. The recognition network can correctly identify the secret image inside the stego image which reaches 98.3% recognition accuracy on MNIST dataset and 91.6% recognition accuracy on CelebA dataset in the covert domain, less than 1% recognition decrease compared with direct recognition. In summary, our approach can successfully identify the secret image without revealing its content. Across various datasets, both the classification accuracy and the invisibility of private images are consistently satisfactory.
{"title":"Hide and Recognize Your Privacy Image","authors":"Zhiying Zhu;Hang Zhou;Haoqi Hu;Qingchao Jiang;Zhenxing Qian;Xinpeng Zhang","doi":"10.1109/TNSE.2024.3456103","DOIUrl":"10.1109/TNSE.2024.3456103","url":null,"abstract":"Recent studies have demonstrated that deep neural networks show excellent performance in information hiding. Considering the tremendous progress that deep learning has made in image recognition, we explore whether neural networks can recognize invisible private images hidden in cover images. In this article, we propose a method for image recognition in the covert domain using neural networks. Our target is to hide an image inside another image with minimal visual quality loss, while at the same time, the hidden image can be recognized correctly without being recovered. In the proposed system, the hiding and recognition of secret images are all performed by neural networks. The hiding network and the recognition network are designed to specifically work as a pair. We design and jointly train preparation, hiding, and recognition networks, where given a cover and a secret image, the preparation network reduces redundant information of the secret image, the hiding network produces a stego image that is visually indistinguishable from the cover image, and the PSNR and SSIM reach 38.5 dB and 0.991 on the MNIST & CIFAR-10 dataset and 41.8 dB and 0.995 on the CelebA & Scene dataset, respectively. The recognition network can correctly identify the secret image inside the stego image which reaches 98.3% recognition accuracy on MNIST dataset and 91.6% recognition accuracy on CelebA dataset in the covert domain, less than 1% recognition decrease compared with direct recognition. In summary, our approach can successfully identify the secret image without revealing its content. Across various datasets, both the classification accuracy and the invisibility of private images are consistently satisfactory.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"6130-6142"},"PeriodicalIF":6.7,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aviation networks consist of networks of flight services provided by numerous airlines and are represented in the form of multiplex networks composed of a set of nodes, multiple layers of links, and coupling node relationships across all layers. However, multiplex aviation networks (MANs) are vulnerable to disturbances due to potential cascading failures. Thus, the robustness of MANs must be maintained. Previous studies on the robustness of MANs have mainly focused on the pairwise interactions between two nodes, which are insufficient for characterizing the dynamic processes of actual MANs. In addition, current cascading failure models are not adequate for MANs, as flow must be redistributed within multiplex networks rather than to nearby airports. To solve these issues, this study developed a topology model of MANs and introduced a model of node congestion to simulate the cascading failure process. Given the robustness assessment of MANs under intentional attacks, numerous analyses of higher-order interactions in networks are conducted. A higher-order cycle structure rewiring strategy is proposed to enhance the dynamic interaction among the layers and further improve the robustness of the MANs. Extensive experiments on synthetic and actual EU-Air multiplex networks are presented to illustrate the superiority of the proposed approach over state-of-the-art algorithms in improving the robustness of MANs.
{"title":"Higher-Order Rewiring Strategy for Enhancing Robustness of Multiplex Aviation Networks","authors":"Dongming Fan;Meng Liu;Xingshuo Hai;Yi Ren;Qiang Feng","doi":"10.1109/TNSE.2024.3422471","DOIUrl":"10.1109/TNSE.2024.3422471","url":null,"abstract":"Aviation networks consist of networks of flight services provided by numerous airlines and are represented in the form of multiplex networks composed of a set of nodes, multiple layers of links, and coupling node relationships across all layers. However, multiplex aviation networks (MANs) are vulnerable to disturbances due to potential cascading failures. Thus, the robustness of MANs must be maintained. Previous studies on the robustness of MANs have mainly focused on the pairwise interactions between two nodes, which are insufficient for characterizing the dynamic processes of actual MANs. In addition, current cascading failure models are not adequate for MANs, as flow must be redistributed within multiplex networks rather than to nearby airports. To solve these issues, this study developed a topology model of MANs and introduced a model of node congestion to simulate the cascading failure process. Given the robustness assessment of MANs under intentional attacks, numerous analyses of higher-order interactions in networks are conducted. A higher-order cycle structure rewiring strategy is proposed to enhance the dynamic interaction among the layers and further improve the robustness of the MANs. Extensive experiments on synthetic and actual EU-Air multiplex networks are presented to illustrate the superiority of the proposed approach over state-of-the-art algorithms in improving the robustness of MANs.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"6417-6430"},"PeriodicalIF":6.7,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-11DOI: 10.1109/TNSE.2024.3459087
Jing Zhang;Zichen Pan;Jie Cui;Hong Zhong;Jiaxin Li;Debiao He
Vehicular intrusion detection systems (IDS) are crucial to ensure the security of vehicular ad hoc networks (VANETs). However, most current IDS for vehicles have been developed using closed datasets, resulting in a limited detection range. Furthermore, in the real world, updates to IDS often fall behind the emergence of novel and unknown attacks, rendering these systems ineffective in defending against such attacks. To overcome this limitation and protect against network attacks in open scenarios, we propose a novel vehicular intrusion detection method that uses meta-recognition. This method utilizes a new neural network to extract joint features and calibrate the predicted values of a pre-trained model via extreme value theory (EVT). In addition, to adapt to the VANETs environment, we introduce temperature scaling and tail separation sampling methods to enhance the modeling effect and increase the prediction accuracy. Comprehensive experiments indicated that the proposed method can detect known attacks at a fine-grained level, identify unknown attacks, and outperform the current state-of-the-art schemes.
{"title":"Toward Open-Set Intrusion Detection in VANETs: An Efficient Meta-Recognition Approach","authors":"Jing Zhang;Zichen Pan;Jie Cui;Hong Zhong;Jiaxin Li;Debiao He","doi":"10.1109/TNSE.2024.3459087","DOIUrl":"10.1109/TNSE.2024.3459087","url":null,"abstract":"Vehicular intrusion detection systems (IDS) are crucial to ensure the security of vehicular ad hoc networks (VANETs). However, most current IDS for vehicles have been developed using closed datasets, resulting in a limited detection range. Furthermore, in the real world, updates to IDS often fall behind the emergence of novel and unknown attacks, rendering these systems ineffective in defending against such attacks. To overcome this limitation and protect against network attacks in open scenarios, we propose a novel vehicular intrusion detection method that uses meta-recognition. This method utilizes a new neural network to extract joint features and calibrate the predicted values of a pre-trained model via extreme value theory (EVT). In addition, to adapt to the VANETs environment, we introduce temperature scaling and tail separation sampling methods to enhance the modeling effect and increase the prediction accuracy. Comprehensive experiments indicated that the proposed method can detect known attacks at a fine-grained level, identify unknown attacks, and outperform the current state-of-the-art schemes.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"6589-6604"},"PeriodicalIF":6.7,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1109/TNSE.2024.3457911
Zhi Lian;Peng Shi;Chee Peng Lim;Imre J. Rudas;Ramesh K. Agarwal
Security related issues of cyber-physical systems are important and interesting from the perspectives of both attackers and defenders. In this paper, we design a stochastic event-based stealthy hybrid attack scheme for remote state estimation in the event of packet dropouts. The objective of the attacker is to maximize the performance degradation while remaining stealthy. Firstly, attack stealthiness is characterized based on the probability distribution and transmission rate. With the stealthiness constraints, an innovation-based stealthy attack model is designed under the assumption that attackers can intercept and modify the measurement innovations. Then, an optimal hybrid attack technique is proposed to maximize the estimation error. With the developed attack strategy, attackers can launch hybrid attacks, including denial-of-service attacks and/or false data injection attacks, to block the network communication channel and compromise the transmitted measurements, therefore degrading and even destroying the system performance. Verification examples are given to illustrate the effectiveness of the attack design performance.
{"title":"Hybrid Stealthy Attacks on Stochastic Event-Based Remote Estimation Under Packet Dropouts","authors":"Zhi Lian;Peng Shi;Chee Peng Lim;Imre J. Rudas;Ramesh K. Agarwal","doi":"10.1109/TNSE.2024.3457911","DOIUrl":"10.1109/TNSE.2024.3457911","url":null,"abstract":"Security related issues of cyber-physical systems are important and interesting from the perspectives of both attackers and defenders. In this paper, we design a stochastic event-based stealthy hybrid attack scheme for remote state estimation in the event of packet dropouts. The objective of the attacker is to maximize the performance degradation while remaining stealthy. Firstly, attack stealthiness is characterized based on the probability distribution and transmission rate. With the stealthiness constraints, an innovation-based stealthy attack model is designed under the assumption that attackers can intercept and modify the measurement innovations. Then, an optimal hybrid attack technique is proposed to maximize the estimation error. With the developed attack strategy, attackers can launch hybrid attacks, including denial-of-service attacks and/or false data injection attacks, to block the network communication channel and compromise the transmitted measurements, therefore degrading and even destroying the system performance. Verification examples are given to illustrate the effectiveness of the attack design performance.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"5829-5838"},"PeriodicalIF":6.7,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1109/TNSE.2024.3457382
Yue Yang;Yang Xiao;Tieshan Li;Kezhong Liu
As an effective multi-agent system (MAS) control method, formation control is widely used in uncrewed systems, such as uncrewed surface/underwater/aerial vehicles and spacecrafts. However, the security issues of formation control have received little attention. Compared with traditional industry systems (such as smart grids or intelligence appliances), designing countermeasure approaches for distributed formation systems under attacks has several challenges, such as limited local information, robot mobility, and a chain reaction of attacks. In this paper, based on a classical formation control law on a group of robots, we concentrate on maintaining an acceptable formation performance under Man-in-the-Middle-based (MITM-based) displacement attacks. The MITM-based displacement attacks can utilize the property of formation maintenance and hijack the whole robot group. We propose two kinds of novel countermeasure approaches. An active approach, which is named the comparison-based identification and elimination (CIE) algorithm, can identify attack messages and calculate estimate values to replace attack messages based on local information. A passive approach can tolerate attack effects by designing a task priority adjustment (TPA) controller. The TPA controller can gradually adjust the formation maintenance priority to degrade attack effects. Simulation with several nonholonomic differentially driven mobile robots is conducted, and results show that our schemes can significantly decrease the impact of constant and time-varying attacks.
{"title":"Defense for Displacement Attacks on Distributed Formation Control Systems","authors":"Yue Yang;Yang Xiao;Tieshan Li;Kezhong Liu","doi":"10.1109/TNSE.2024.3457382","DOIUrl":"10.1109/TNSE.2024.3457382","url":null,"abstract":"As an effective multi-agent system (MAS) control method, formation control is widely used in uncrewed systems, such as uncrewed surface/underwater/aerial vehicles and spacecrafts. However, the security issues of formation control have received little attention. Compared with traditional industry systems (such as smart grids or intelligence appliances), designing countermeasure approaches for distributed formation systems under attacks has several challenges, such as limited local information, robot mobility, and a chain reaction of attacks. In this paper, based on a classical formation control law on a group of robots, we concentrate on maintaining an acceptable formation performance under Man-in-the-Middle-based (MITM-based) displacement attacks. The MITM-based displacement attacks can utilize the property of formation maintenance and hijack the whole robot group. We propose two kinds of novel countermeasure approaches. An active approach, which is named the comparison-based identification and elimination (CIE) algorithm, can identify attack messages and calculate estimate values to replace attack messages based on local information. A passive approach can tolerate attack effects by designing a task priority adjustment (TPA) controller. The TPA controller can gradually adjust the formation maintenance priority to degrade attack effects. Simulation with several nonholonomic differentially driven mobile robots is conducted, and results show that our schemes can significantly decrease the impact of constant and time-varying attacks.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"6560-6573"},"PeriodicalIF":6.7,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Given the urgency of climate change, many countries have set carbon neutrality targets and adopted cap-and-trade (C&T) systems to regulate carbon emissions. Accurate carbon emission data is crucial for the effective operation of carbon pricing and management systems. Monitoring, Reporting, and Verification (MRV) system is at the core of these systems, facing challenges such as, inefficient verification process, and low-quality carbon emissions verification. Blockchain and smart contracts offer promising solutions to some difficulties, while the quality of carbon emissions verification still needs improvement. Therefore, we propose a blockchain-enhanced carbon emissions verification model to optimize system efficiency and support compliance verification. We employ reputation as the admission criterion, screening reliable and trustworthy verification candidates. We design a game-theoretic incentive mechanism implemented through smart contracts to promote compliance and collaborative quality control among participants. Analysis shows that our scheme drives the game model towards the Nash equilibrium that achieves collaborative quality control. Through security analysis and simulation experiments, we verify the efficacy of our mechanism concerning verification quality and procedural automation, confirming its potential to mitigate malpractices and enhance consistent compliance.
{"title":"Game-Theoretic Incentive Mechanism for Collaborative Quality Control in Blockchain-Enhanced Carbon Emissions Verification","authors":"Yunhua He;Zhihao Zhou;Bin Wu;Ke Xiao;Chao Wang;Xiuzhen Cheng","doi":"10.1109/TNSE.2024.3456116","DOIUrl":"10.1109/TNSE.2024.3456116","url":null,"abstract":"Given the urgency of climate change, many countries have set carbon neutrality targets and adopted cap-and-trade (C&T) systems to regulate carbon emissions. Accurate carbon emission data is crucial for the effective operation of carbon pricing and management systems. Monitoring, Reporting, and Verification (MRV) system is at the core of these systems, facing challenges such as, inefficient verification process, and low-quality carbon emissions verification. Blockchain and smart contracts offer promising solutions to some difficulties, while the quality of carbon emissions verification still needs improvement. Therefore, we propose a blockchain-enhanced carbon emissions verification model to optimize system efficiency and support compliance verification. We employ reputation as the admission criterion, screening reliable and trustworthy verification candidates. We design a game-theoretic incentive mechanism implemented through smart contracts to promote compliance and collaborative quality control among participants. Analysis shows that our scheme drives the game model towards the Nash equilibrium that achieves collaborative quality control. Through security analysis and simulation experiments, we verify the efficacy of our mechanism concerning verification quality and procedural automation, confirming its potential to mitigate malpractices and enhance consistent compliance.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"6535-6549"},"PeriodicalIF":6.7,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-09DOI: 10.1109/TNSE.2024.3456231
Conghua Wang;Yuan Zhang;Tingwen Huang;Zhichun Yang
In immune systems, the innate immune response and CD8 T cells play a crucial synergistic role in combating viral pathogens. In this paper, we develop a delayed viral infection model to investigate the dynamic mechanisms governing infection outcomes. The model categorizes viral infections into five states: clearance, mild, moderate, heavy, and recurrent. A key finding is that diminished innate immune responses create a bistable condition, enabling the initial antigen load and the length of the viral incubation period to act as toggle switches that determine whether infections will be mild or heavy. Furthermore, the viral incubation period induces a Hopf bifurcation, changing mild infections from a stable state to periodic oscillations, potentially leading to recurrent infections. Interestingly, enhancing the innate immune response not only bolsters the CD8 T cell-mediated destruction of infected cells but also delays the onset of the Hopf bifurcation and reduces the adverse effects of incubation periods. These insights suggest that strengthening the innate immune response and developing drugs to shorten the incubation period are viable strategies to combat viral infections.
在免疫系统中，先天免疫反应和 CD8 T 细胞在抗击病毒病原体方面发挥着至关重要的协同作用。在本文中，我们建立了一个延迟病毒感染模型，以研究支配感染结果的动态机制。该模型将病毒感染分为五种状态：清除、轻度、中度、重度和复发。一个重要发现是，先天免疫反应的减弱造成了一种双稳态状态，使初始抗原负荷和病毒潜伏期的长短成为决定感染是轻度还是重度的切换开关。此外，病毒潜伏期会诱发霍普夫分岔，使轻度感染从稳定状态转变为周期性振荡，从而可能导致反复感染。有趣的是，增强先天性免疫反应不仅能促进 CD8 T 细胞介导的对感染细胞的破坏，还能延缓霍普夫分岔的发生，减少潜伏期的不利影响。这些见解表明，加强先天免疫反应和开发缩短潜伏期的药物是对抗病毒感染的可行策略。
{"title":"Dynamics and Regulatory Mechanisms of Innate Immunity and CD8 T Cells Synergy in Response to Viral Infections","authors":"Conghua Wang;Yuan Zhang;Tingwen Huang;Zhichun Yang","doi":"10.1109/TNSE.2024.3456231","DOIUrl":"10.1109/TNSE.2024.3456231","url":null,"abstract":"In immune systems, the innate immune response and CD8 T cells play a crucial synergistic role in combating viral pathogens. In this paper, we develop a delayed viral infection model to investigate the dynamic mechanisms governing infection outcomes. The model categorizes viral infections into five states: clearance, mild, moderate, heavy, and recurrent. A key finding is that diminished innate immune responses create a bistable condition, enabling the initial antigen load and the length of the viral incubation period to act as toggle switches that determine whether infections will be mild or heavy. Furthermore, the viral incubation period induces a Hopf bifurcation, changing mild infections from a stable state to periodic oscillations, potentially leading to recurrent infections. Interestingly, enhancing the innate immune response not only bolsters the CD8 T cell-mediated destruction of infected cells but also delays the onset of the Hopf bifurcation and reduces the adverse effects of incubation periods. These insights suggest that strengthening the innate immune response and developing drugs to shorten the incubation period are viable strategies to combat viral infections.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"6550-6559"},"PeriodicalIF":6.7,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-09DOI: 10.1109/TNSE.2024.3454993
Qi Shao;Duxin Chen;Wenwu Yu
Graph contrastive learning has gained significant attention for its effectiveness in leveraging unlabeled data and achieving superior performance. However, prevalent graph contrastive learning methods often resort to graph augmentation, typically involving the removal of anchor graph structures. This strategy may compromise the essential graph information, constraining the adaptability of contrastive learning approaches across diverse tasks. To overcome this limitation, we introduce a novel augmentation technique for graph contrastive learning: heterogeneous augmentation . Through the application of heterogeneous augmentation to homogeneous anchor graphs, our method obviates the need for modifying edges and nodes, preserving the structural integrity of the anchor graph to the fullest extent. The proposed method could become a significant technique in graph augmentation, potentially influencing further research and development in this area. Our work provides a valuable contribution to the advancement of graph contrastive learning methodologies.
{"title":"A Unique Framework of Heterogeneous Augmentation Graph Contrastive Learning for Both Node and Graph Classification","authors":"Qi Shao;Duxin Chen;Wenwu Yu","doi":"10.1109/TNSE.2024.3454993","DOIUrl":"10.1109/TNSE.2024.3454993","url":null,"abstract":"Graph contrastive learning has gained significant attention for its effectiveness in leveraging unlabeled data and achieving superior performance. However, prevalent graph contrastive learning methods often resort to graph augmentation, typically involving the removal of anchor graph structures. This strategy may compromise the essential graph information, constraining the adaptability of contrastive learning approaches across diverse tasks. To overcome this limitation, we introduce a novel augmentation technique for graph contrastive learning: \u0000<italic>heterogeneous augmentation</i>\u0000. Through the application of heterogeneous augmentation to homogeneous anchor graphs, our method obviates the need for modifying edges and nodes, preserving the structural integrity of the anchor graph to the fullest extent. The proposed method could become a significant technique in graph augmentation, potentially influencing further research and development in this area. Our work provides a valuable contribution to the advancement of graph contrastive learning methodologies.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"5818-5828"},"PeriodicalIF":6.7,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Predicting edge-side cellular network traffic stands as a pivotal facilitator for network automation in next-generation communication systems. However, the traffic data at the edge exhibits significant heterogeneity, inhomogeneity, and volatility due to geographic location, human activities, and demand diversification, thus making accurate network traffic prediction a rigorous challenge. To solve this problem, this paper proposes a novel cellular network traffic prediction model in the edge-managed multi-base station (BS) scenarios, named trend graph characterization network (TGCN). Structurally, TGCN has three key components of trend feature extractor, temporal feature extractor and predictor. Firstly, the high-dimensional trend feature of traffic can be captured by the combination of ordinal pattern transition network (OPTN) and graph attention network (GAT). Furthermore, in the temporal feature extractor neural circuit policy (NCP) is introduced for multi-scale time-varying dependent features. Finally, a fully-connected layer serves as the approximator of BS traffic. On real-world datasets, we verify the superiority of our proposal via statistical analysis, prediction accuracy and ablation experiments.
{"title":"Edge-Side Cellular Network Traffic Prediction Based on Trend Graph Characterization Network","authors":"Mingxiang Hao;Xiaochuan Sun;Yingqi Li;Haijun Zhang","doi":"10.1109/TNSE.2024.3455784","DOIUrl":"10.1109/TNSE.2024.3455784","url":null,"abstract":"Predicting edge-side cellular network traffic stands as a pivotal facilitator for network automation in next-generation communication systems. However, the traffic data at the edge exhibits significant heterogeneity, inhomogeneity, and volatility due to geographic location, human activities, and demand diversification, thus making accurate network traffic prediction a rigorous challenge. To solve this problem, this paper proposes a novel cellular network traffic prediction model in the edge-managed multi-base station (BS) scenarios, named trend graph characterization network (TGCN). Structurally, TGCN has three key components of trend feature extractor, temporal feature extractor and predictor. Firstly, the high-dimensional trend feature of traffic can be captured by the combination of ordinal pattern transition network (OPTN) and graph attention network (GAT). Furthermore, in the temporal feature extractor neural circuit policy (NCP) is introduced for multi-scale time-varying dependent features. Finally, a fully-connected layer serves as the approximator of BS traffic. On real-world datasets, we verify the superiority of our proposal via statistical analysis, prediction accuracy and ablation experiments.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"6118-6129"},"PeriodicalIF":6.7,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142191984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：