The surge in location-based services has driven the demand for accurate indoor localization techniques, with WiFi-based localization emerging as a promising solution due to its extensive coverage in indoor environments. This paper presents BFI-L10 N, an indoor localization method that leverages beamforming feedback information (BFI) obtained from standard multi-user multiple-input multiple-output (MU-MIMO) WiFi operations. Unlike traditional channel state information (CSI)-based methods that require vendor-specific firmware patches or restricted device support, BFI leverages standardized MU-MIMO operations, enabling compatibility with off-the-shelf WiFi devices. BFI-L10 N processes the BFI data collected during the beamforming process through a deep learning framework and uses a BERT model for localization. Compared to CSI-based systems, BFI-L10 N offers advantages such as reduced overhead, enhanced sensitivity, compatibility with standard devices, and real-time predictions. Our experimental results in two distinct indoor environments demonstrate that BFI-L10 N achieves average localization accuracies of 10.7 cm and 15.5 cm in a research laboratory and a conference room, respectively, outperforming the state-of-the-art CSI techniques by 28%. Moreover, the BERT model can be fine-tuned after pre-training across multiple locations, which enhances the versatility of BFI-L10 N. This paper presents a novel perspective on WiFi sensing and lays the foundation for practical indoor localization using standard WiFi infrastructure.
{"title":"BFI-L10 N: Learning Beamforming Feedback Information for Indoor Localization","authors":"Jiayu Chen;Shuai Wang;Yunhuai Liu;Tian He;Shuai Wang;Demin Gao","doi":"10.1109/TMC.2025.3632807","DOIUrl":"https://doi.org/10.1109/TMC.2025.3632807","url":null,"abstract":"The surge in location-based services has driven the demand for accurate indoor localization techniques, with WiFi-based localization emerging as a promising solution due to its extensive coverage in indoor environments. This paper presents BFI-L10 N, an indoor localization method that leverages beamforming feedback information (BFI) obtained from standard multi-user multiple-input multiple-output (MU-MIMO) WiFi operations. Unlike traditional channel state information (CSI)-based methods that require vendor-specific firmware patches or restricted device support, BFI leverages standardized MU-MIMO operations, enabling compatibility with off-the-shelf WiFi devices. BFI-L10 N processes the BFI data collected during the beamforming process through a deep learning framework and uses a BERT model for localization. Compared to CSI-based systems, BFI-L10 N offers advantages such as reduced overhead, enhanced sensitivity, compatibility with standard devices, and real-time predictions. Our experimental results in two distinct indoor environments demonstrate that BFI-L10 N achieves average localization accuracies of 10.7 cm and 15.5 cm in a research laboratory and a conference room, respectively, outperforming the state-of-the-art CSI techniques by 28%. Moreover, the BERT model can be fine-tuned after pre-training across multiple locations, which enhances the versatility of BFI-L10 N. This paper presents a novel perspective on WiFi sensing and lays the foundation for practical indoor localization using standard WiFi infrastructure.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 4","pages":"5839-5854"},"PeriodicalIF":9.2,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147362442","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 : 2025-11-14DOI: 10.1109/TMC.2025.3632863
Zhengzhi Yang;Yuanhao Cui;Wenbo Du;Fanbiao Li;Yumeng Li
As an emerging countermeasure, cooperative interception by multiple UAVs offers an effective solution to neutralize rogue drones and safeguard low-altitude airspace operations. Effective coordination among counter-UAVs in encircling intruding drones remains challenging. This paper proposes a Hierarchical Cooperative Deep Reinforcement Learning (HCDRL) algorithm to enhance cooperation and efficiency among UAVs pursuing agile targets. The proposed approach decomposes the multi-agent pursuit-evasion scenario into multiple subtasks using a two-layer hierarchical decision-making framework. Specifically, the upper-layer network acts as a meta-strategy, dynamically assessing pursuit scenarios and assigning optimal subtasks. Meanwhile, the lower-layer policy networks of individual agents determine maneuver actions based on local observations and assigned subtasks. Simulation results demonstrate that the proposed algorithm significantly improves multi-agent cooperative encirclement performance, achieving an 11.18% higher success rate and a 9.94% reduction in completion time compared to state-of-the-art methods.
{"title":"Cooperative Pursuit-Evasion With Low Altitude Wireless Network: A Hierarchical Reinforcement Learning Approach","authors":"Zhengzhi Yang;Yuanhao Cui;Wenbo Du;Fanbiao Li;Yumeng Li","doi":"10.1109/TMC.2025.3632863","DOIUrl":"https://doi.org/10.1109/TMC.2025.3632863","url":null,"abstract":"As an emerging countermeasure, cooperative interception by multiple UAVs offers an effective solution to neutralize rogue drones and safeguard low-altitude airspace operations. Effective coordination among counter-UAVs in encircling intruding drones remains challenging. This paper proposes a Hierarchical Cooperative Deep Reinforcement Learning (HCDRL) algorithm to enhance cooperation and efficiency among UAVs pursuing agile targets. The proposed approach decomposes the multi-agent pursuit-evasion scenario into multiple subtasks using a two-layer hierarchical decision-making framework. Specifically, the upper-layer network acts as a meta-strategy, dynamically assessing pursuit scenarios and assigning optimal subtasks. Meanwhile, the lower-layer policy networks of individual agents determine maneuver actions based on local observations and assigned subtasks. Simulation results demonstrate that the proposed algorithm significantly improves multi-agent cooperative encirclement performance, achieving an 11.18% higher success rate and a 9.94% reduction in completion time compared to state-of-the-art methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 4","pages":"5716-5729"},"PeriodicalIF":9.2,"publicationDate":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147362556","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 : 2025-10-24DOI: 10.1109/TMC.2025.3625547
Jin Cheng;Ningning Ding;John C.S. Lui;Jianwei Huang
In the Big Data era, data trading significantly enhances data-driven decision-making by facilitating data sharing. Streaming data from sources such as mobile devices and social media platforms creates new opportunities and challenges for data trading. Traditional data trading methods, designed for one-time queries over static database snapshots, neglect the growing need for trading continuous queries over streaming data. If applied directly to continuous queries, existing methods often result in repeated and imprecise charges that reduce the seller's profit, as they do not consider computation sharing during continuous query execution. To address these challenges, we propose CQTrade, the first mechanism for continuous query-based data trading, which incorporates computation sharing in query execution and integrates seamlessly with existing trading mechanisms. Our contributions are threefold: (1) we provide a theoretical analysis of prevalent computation-sharing techniques, including cost modeling and closed-form computation-sharing strategy derivation; (2) we formulate a general optimization problem to maximize the seller's profit, adaptable to various computation-sharing techniques; (3) we identify that our optimization problem merges vector bin packing and multidimensional knapsack challenges, and we tackle this complexity with a tailored branch-and-price algorithm that decomposes the problem into a masterproblem and multiple sub-problems, achieving a globally optimal solution. Evaluation shows CQTrade improves trading success rate by 12.8% and increases seller profit by 28.7% compared to traditional methods.
{"title":"Trading Continuous Queries","authors":"Jin Cheng;Ningning Ding;John C.S. Lui;Jianwei Huang","doi":"10.1109/TMC.2025.3625547","DOIUrl":"https://doi.org/10.1109/TMC.2025.3625547","url":null,"abstract":"In the Big Data era, data trading significantly enhances data-driven decision-making by facilitating data sharing. Streaming data from sources such as mobile devices and social media platforms creates new opportunities and challenges for data trading. Traditional data trading methods, designed for one-time queries over static database snapshots, neglect the growing need for trading continuous queries over streaming data. If applied directly to continuous queries, existing methods often result in repeated and imprecise charges that reduce the seller's profit, as they do not consider computation sharing during continuous query execution. To address these challenges, we propose CQTrade, the first mechanism for continuous query-based data trading, which incorporates computation sharing in query execution and integrates seamlessly with existing trading mechanisms. Our contributions are threefold: (1) we provide a theoretical analysis of prevalent computation-sharing techniques, including cost modeling and closed-form computation-sharing strategy derivation; (2) we formulate a general optimization problem to maximize the seller's profit, adaptable to various computation-sharing techniques; (3) we identify that our optimization problem merges vector bin packing and multidimensional knapsack challenges, and we tackle this complexity with a tailored branch-and-price algorithm that decomposes the problem into a masterproblem and multiple sub-problems, achieving a globally optimal solution. Evaluation shows CQTrade improves trading success rate by 12.8% and increases seller profit by 28.7% compared to traditional methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 3","pages":"4253-4268"},"PeriodicalIF":9.2,"publicationDate":"2025-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146116802","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 : 2025-10-23DOI: 10.1109/TMC.2025.3624756
Wenbin Huang;Ju Ren;Hangcheng Cao;Hongbo Jiang;Panlong Yang;Zhangjie Fu
Voice-enabled mobile applications (apps) are exploding in popularity as they could be manipulated with voice commands to achieve convenient man-machine interaction. These voice-enabled apps also raise security and privacy concerns about whether they would maliciously invoke microphones to realize voice eavesdropping. To explore this issue, in this work, we design baleful apps to access the microphone covertly, the results of test studies demonstrate that covert eavesdropping attacks can bypass existing device detection schemes as well as are unnoticeable to human users. To prevent the covert voice eavesdropping attack, we propose a versatile microphone icon detection (MicID) scheme inspired by the groundtruth that authorization of the voice function requires the user to touch the specific microphone icon in most of voice-based apps. Specifically, we devise a deep learning model, lightweight YOLO (L-YOLO), to locate the microphone icon on the screen quickly and accurately. By determining whether the located microphone icon is touched by the user, we can judge whether the current microphone access belongs to the app’s normal operation or illegal eavesdropping. Finally, we conduct extensive experiments by deploying the scheme on real devices and collecting dataset. The evaluation results show that the proposed MicID scheme achieves more than 99% accuracy with low computation cost.
{"title":"Learning Based Versatile Voice Eavesdropping Prevention for Mobile Devices","authors":"Wenbin Huang;Ju Ren;Hangcheng Cao;Hongbo Jiang;Panlong Yang;Zhangjie Fu","doi":"10.1109/TMC.2025.3624756","DOIUrl":"https://doi.org/10.1109/TMC.2025.3624756","url":null,"abstract":"Voice-enabled <italic>mobile applications</i> (apps) are exploding in popularity as they could be manipulated with voice commands to achieve convenient man-machine interaction. These voice-enabled apps also raise security and privacy concerns about whether they would maliciously invoke microphones to realize voice eavesdropping. To explore this issue, in this work, we design baleful apps to access the microphone covertly, the results of test studies demonstrate that covert eavesdropping attacks can bypass existing device detection schemes as well as are unnoticeable to human users. To prevent the covert voice eavesdropping attack, we propose a versatile <italic>microphone icon detection</i> (MicID) scheme inspired by the groundtruth that authorization of the voice function requires the user to touch the specific microphone icon in most of voice-based apps. Specifically, we devise a deep learning model, <italic>lightweight YOLO</i> (L-YOLO), to locate the microphone icon on the screen quickly and accurately. By determining whether the located microphone icon is touched by the user, we can judge whether the current microphone access belongs to the app’s normal operation or illegal eavesdropping. Finally, we conduct extensive experiments by deploying the scheme on real devices and collecting dataset. The evaluation results show that the proposed MicID scheme achieves more than 99% accuracy with low computation cost.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 3","pages":"4393-4408"},"PeriodicalIF":9.2,"publicationDate":"2025-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146116834","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 : 2025-10-23DOI: 10.1109/TMC.2025.3624628
Kai Peng;Tongxin Liao;Mingyuan Ren;Yi Hu;Liangliang Wu;Menglan Hu;Hongbo Jiang
With the rapid advancement of edge computing, service mesh has emerged as a critical technology for improving network performance, owing to its flexibility and scalability. However, massive online applications in edge clouds pose significant challenges to microservice orchestration, including high concurrency, complex service dependencies, strict response delay requirements, and fast orchestration needs. Addressing these challenges requires efficient and fast orchestration strategies, but existing approaches often lack accurate models and effective algorithms to handle these complexities. To tackle the above challenges, this paper proposes an efficient Symmetric Microservice Deployment (SMD) algorithm for fast orchestration. First, accurate modeling is achieved with the queuing network, which analyzes intertwined requests and calculates detailed delays. Moreover, the SMD algorithm simplifies the coupling between deployment and routing by considering internal dependencies during deployment. This integrated approach eliminates the need for separate routing solutions and ensures provable optimal performance under symmetric deployment. Experimental results demonstrate that, compared to four baseline algorithms, the proposed method reduces response delay by 25.5% and execution time by 58.4%, showcasing the potential and advantages of the algorithm for optimizing microservice orchestration in edge clouds networks.
{"title":"Symmetric Orchestration Under Service Mesh Paradigm: Empowering Massive Online Applications in Edge Clouds","authors":"Kai Peng;Tongxin Liao;Mingyuan Ren;Yi Hu;Liangliang Wu;Menglan Hu;Hongbo Jiang","doi":"10.1109/TMC.2025.3624628","DOIUrl":"https://doi.org/10.1109/TMC.2025.3624628","url":null,"abstract":"With the rapid advancement of edge computing, service mesh has emerged as a critical technology for improving network performance, owing to its flexibility and scalability. However, massive online applications in edge clouds pose significant challenges to microservice orchestration, including high concurrency, complex service dependencies, strict response delay requirements, and fast orchestration needs. Addressing these challenges requires efficient and fast orchestration strategies, but existing approaches often lack accurate models and effective algorithms to handle these complexities. To tackle the above challenges, this paper proposes an efficient Symmetric Microservice Deployment (SMD) algorithm for fast orchestration. First, accurate modeling is achieved with the queuing network, which analyzes intertwined requests and calculates detailed delays. Moreover, the SMD algorithm simplifies the coupling between deployment and routing by considering internal dependencies during deployment. This integrated approach eliminates the need for separate routing solutions and ensures provable optimal performance under symmetric deployment. Experimental results demonstrate that, compared to four baseline algorithms, the proposed method reduces response delay by 25.5% and execution time by 58.4%, showcasing the potential and advantages of the algorithm for optimizing microservice orchestration in edge clouds networks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 3","pages":"4300-4316"},"PeriodicalIF":9.2,"publicationDate":"2025-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146116851","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}
Exploiting on-device data and computing power for machine learning at the network edge is challenged by constrained device resources, privacy requirements, and local data heterogeneity. To address the above gap, this work proposes a dual-functional blockchain framework named BagChain for bagging-based decentralized ML. BagChain integrates blockchain with distributed ML by replacing the computationally costly hash computing in proof-of-work with ML model training and validation, and does not rely on any trusted central servers. Individual miners in BagChain train base models by using their local computing resources and private data and further aggregate these base models, which could be very weak, into strong ensemble models. More specifically, we design a three-layer blockchain structure and associated generation and validation mechanisms to enable distributed ML among uncoordinated miners without revealing raw data. To reduce computational waste due to blockchain forking, we further propose the cross fork sharing mechanism for practical networks with lengthy delay and limited bandwidth. Extensive experiments illustrate the superiority and efficacy of BagChain when handling various ML tasks on both independently and identically distributed (IID) and non-IID datasets. BagChain remains robust and effective even when facing resource-constrained mobile devices, heterogeneous private user data, and limited network connectivity.
{"title":"BagChain: A Dual-Functional Blockchain Leveraging Bagging-Based Distributed Machine Learning","authors":"Zixiang Cui;Xintong Ling;Xingyu Zhou;Jiaheng Wang;Zhi Ding;Xiqi Gao","doi":"10.1109/TMC.2025.3624804","DOIUrl":"https://doi.org/10.1109/TMC.2025.3624804","url":null,"abstract":"Exploiting on-device data and computing power for machine learning at the network edge is challenged by constrained device resources, privacy requirements, and local data heterogeneity. To address the above gap, this work proposes a dual-functional blockchain framework named BagChain for bagging-based decentralized ML. BagChain integrates blockchain with distributed ML by replacing the computationally costly hash computing in proof-of-work with ML model training and validation, and does not rely on any trusted central servers. Individual miners in BagChain train base models by using their local computing resources and private data and further aggregate these base models, which could be very weak, into strong ensemble models. More specifically, we design a three-layer blockchain structure and associated generation and validation mechanisms to enable distributed ML among uncoordinated miners without revealing raw data. To reduce computational waste due to blockchain forking, we further propose the cross fork sharing mechanism for practical networks with lengthy delay and limited bandwidth. Extensive experiments illustrate the superiority and efficacy of BagChain when handling various ML tasks on both independently and identically distributed (IID) and non-IID datasets. BagChain remains robust and effective even when facing resource-constrained mobile devices, heterogeneous private user data, and limited network connectivity.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 3","pages":"4206-4222"},"PeriodicalIF":9.2,"publicationDate":"2025-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146116856","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}
This paper investigates the potential of movable antenna (MA)-enabled micro-mobility to replace UAV-enabled macro-mobility for enhancing physical layer security (PLS) in air-to-ground communications. While UAV trajectory optimization offers high flexibility and Line-of-Sight (LoS) advantages, it suffers from significant energy consumption, latency, and complex trajectory optimization. Conversely, MA technology provides fine-grained spatial reconfiguration (antenna positioning within a confined area) with ultra-low energy overhead and millisecond-scale response, enabling real-time channel manipulation and covert beam steering. To systematically compare these paradigms, we establish a dual-scale mobility framework where a UAV-mounted uniform linear array (ULA) serves as a base station transmitting confidential information to a legitimate user (Bob) in the presence of an eavesdropper (Eve). We formulate non-convex average secrecy rate (ASR) maximization problems for both schemes: 1) MA-based micro-mobility: Jointly optimizing antenna positions and beamforming (BF) vectors under positioning constraints; 2) UAV-based macro-mobility: Jointly optimizing the UAV’s trajectory and BF vectors under kinematic constraints. Extensive simulations reveal distinct operational regimes: MA micro-mobility demonstrates significant ASR advantages in low-transmit-power scenarios or under antenna constraints due to its energy-efficient spatial control. Conversely, UAV macro-mobility excels under resource-sufficient conditions (higher power, larger antenna arrays) by leveraging global mobility for optimal positioning. The findings highlight the complementary strengths of both approaches, suggesting hybrid micro-macro mobility as a promising direction for balancing security, energy efficiency, and deployment complexity in future wireless networks.
{"title":"Can Movable Antenna-Enabled Micro-Mobility Replace UAV-Enabled Macro-Mobility? A Physical Layer Security Perspective","authors":"Kaixuan Li;Kan Yu;Dingyou Ma;Yujia Zhao;Xiaowu Liu;Qixun Zhang;Zhiyong Feng","doi":"10.1109/TMC.2025.3624340","DOIUrl":"https://doi.org/10.1109/TMC.2025.3624340","url":null,"abstract":"This paper investigates the potential of movable antenna (MA)-enabled micro-mobility to replace UAV-enabled macro-mobility for enhancing physical layer security (PLS) in air-to-ground communications. While UAV trajectory optimization offers high flexibility and Line-of-Sight (LoS) advantages, it suffers from significant energy consumption, latency, and complex trajectory optimization. Conversely, MA technology provides fine-grained spatial reconfiguration (antenna positioning within a confined area) with ultra-low energy overhead and millisecond-scale response, enabling real-time channel manipulation and covert beam steering. To systematically compare these paradigms, we establish a dual-scale mobility framework where a UAV-mounted uniform linear array (ULA) serves as a base station transmitting confidential information to a legitimate user (Bob) in the presence of an eavesdropper (Eve). We formulate non-convex average secrecy rate (ASR) maximization problems for both schemes: 1) MA-based micro-mobility: Jointly optimizing antenna positions and beamforming (BF) vectors under positioning constraints; 2) UAV-based macro-mobility: Jointly optimizing the UAV’s trajectory and BF vectors under kinematic constraints. Extensive simulations reveal distinct operational regimes: MA micro-mobility demonstrates significant ASR advantages in low-transmit-power scenarios or under antenna constraints due to its energy-efficient spatial control. Conversely, UAV macro-mobility excels under resource-sufficient conditions (higher power, larger antenna arrays) by leveraging global mobility for optimal positioning. The findings highlight the complementary strengths of both approaches, suggesting hybrid micro-macro mobility as a promising direction for balancing security, energy efficiency, and deployment complexity in future wireless networks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 3","pages":"4317-4330"},"PeriodicalIF":9.2,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146116825","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 : 2025-10-22DOI: 10.1109/TMC.2025.3623732
Jiayun Yan;Jie Chen;Haifeng Qian;Jianting Ning;Debiao He
Mobile social networks (MSNs) are integral to the digital era, but the current architectures raise fundamental challenges to user privacy and security. First, these systems rely on a trusted authority, which causes the single point of failure and raises concerns about data leakage. Second, there is a lack of cryptographic mechanisms to enforce bilateral access control, which ensures mutual consent communication by both senders and receivers. Therefore, it’s necessary to design a system to eliminate single-point trust and accurate consent-based matchmaking access control between users. To address these issues, we propose a decentralized multi-authority identity-based matchmaking encryption (DMA-IBME) scheme, including its formal syntax and security definitions. This primitive enables bilateral access control, which ensures both data privacy and user authenticity. Moreover, we formally prove the security of our scheme in the random oracle model under the standard bilinear Diffie-Hellman ($mathsf {BDH}$) assumption. Performance evaluation demonstrates the efficiency of our scheme. Compared to existing works, our construction reduces the setup time by approximately 50% and the encryption key generation time by 30%. Furthermore, the storage costs for public parameters, encryption keys, and ciphertexts are reduced by approximately 30%, 30%, and 88%, respectively.
{"title":"Decentralized Multi-Authority Accurate Matchmaking Encryption Scheme for Mobile Social Networks","authors":"Jiayun Yan;Jie Chen;Haifeng Qian;Jianting Ning;Debiao He","doi":"10.1109/TMC.2025.3623732","DOIUrl":"https://doi.org/10.1109/TMC.2025.3623732","url":null,"abstract":"Mobile social networks (MSNs) are integral to the digital era, but the current architectures raise fundamental challenges to user privacy and security. First, these systems rely on a trusted authority, which causes the single point of failure and raises concerns about data leakage. Second, there is a lack of cryptographic mechanisms to enforce bilateral access control, which ensures mutual consent communication by both senders and receivers. Therefore, it’s necessary to design a system to eliminate single-point trust and accurate consent-based matchmaking access control between users. To address these issues, we propose a decentralized multi-authority identity-based matchmaking encryption (DMA-IBME) scheme, including its formal syntax and security definitions. This primitive enables bilateral access control, which ensures both data privacy and user authenticity. Moreover, we formally prove the security of our scheme in the random oracle model under the standard bilinear Diffie-Hellman (<inline-formula><tex-math>$mathsf {BDH}$</tex-math></inline-formula>) assumption. Performance evaluation demonstrates the efficiency of our scheme. Compared to existing works, our construction reduces the setup time by approximately 50% and the encryption key generation time by 30%. Furthermore, the storage costs for public parameters, encryption keys, and ciphertexts are reduced by approximately 30%, 30%, and 88%, respectively.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 3","pages":"4381-4392"},"PeriodicalIF":9.2,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146116852","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 : 2025-10-22DOI: 10.1109/TMC.2025.3623636
Long He;Geng Sun;Zemin Sun;Jiacheng Wang;Hongyang Du;Dusit Niyato;Jiangchuan Liu;Victor C. M. Leung
The emergence of space-air-ground integrated multi-access edge computing (SAGIMEC) networks opens a significant opportunity for the rapidly growing low altitude economy (LAE), facilitating the development of various applications by offering efficient communication and computing services. However, the heterogeneous nature of SAGIMEC networks, coupled with the stringent computational and communication requirements of diverse applications in the LAE, introduces considerable challenges in integrating SAGIMEC into the LAE. In this work, we first present a digital twin-assisted SAGIMEC paradigm for LAE, where digital twin enables reliable network monitoring and management, while SAGIMEC provides efficient computing offloading services for Internet of Things sensor devices (ISDs). Then, a joint satellite selection, computation offloading, communication resource allocation, computation resource allocation and uncrewed aerial vehicle (UAV) trajectory control optimization problem ($text{JSC}^{4}text{OP}$) is formulated to maximize the quality of service (QoS) of ISDs. Given the complexity of $text{JSC}^{4}text{OP}$, we propose an online decentralized optimization approach (ODOA) to address the problem. Specifically, $text{JSC}^{4}text{OP}$ is first transformed into a real-time decision-making optimization problem (RDOP) by leveraging Lyapunov optimization. Then, to solve the RDOP, we introduce an online learning-based latency prediction method to predict the uncertain system environment and a game theoretic decision-making method to make real-time decisions. Finally, theoretical analysis confirms the effectiveness of the ODOA. Simulation results show that the proposed ODOA outperforms various benchmark approaches and improves the QoS of ISDs by at least 14.5% compared to deep reinforcement learning (DRL)-based approaches, thereby validating the superiority of the proposed approach.
{"title":"Digital Twin-Assisted Space-Air-Ground Integrated Multi-Access Edge Computing for Low-Altitude Economy: An Online Decentralized Optimization Approach","authors":"Long He;Geng Sun;Zemin Sun;Jiacheng Wang;Hongyang Du;Dusit Niyato;Jiangchuan Liu;Victor C. M. Leung","doi":"10.1109/TMC.2025.3623636","DOIUrl":"https://doi.org/10.1109/TMC.2025.3623636","url":null,"abstract":"The emergence of space-air-ground integrated multi-access edge computing (SAGIMEC) networks opens a significant opportunity for the rapidly growing low altitude economy (LAE), facilitating the development of various applications by offering efficient communication and computing services. However, the heterogeneous nature of SAGIMEC networks, coupled with the stringent computational and communication requirements of diverse applications in the LAE, introduces considerable challenges in integrating SAGIMEC into the LAE. In this work, we first present a digital twin-assisted SAGIMEC paradigm for LAE, where digital twin enables reliable network monitoring and management, while SAGIMEC provides efficient computing offloading services for Internet of Things sensor devices (ISDs). Then, a <u><b>j</b></u>oint <u><b>s</b></u>atellite selection, <u><b>c</b></u>omputation offloading, <u><b>c</b></u>ommunication resource allocation, <u><b>c</b></u>omputation resource allocation and uncrewed aerial vehicle (UAV) trajectory <u><b>c</b></u>ontrol optimization problem (<inline-formula><tex-math>$text{JSC}^{4}text{OP}$</tex-math></inline-formula>) is formulated to maximize the quality of service (QoS) of ISDs. Given the complexity of <inline-formula><tex-math>$text{JSC}^{4}text{OP}$</tex-math></inline-formula>, we propose an online decentralized optimization approach (ODOA) to address the problem. Specifically, <inline-formula><tex-math>$text{JSC}^{4}text{OP}$</tex-math></inline-formula> is first transformed into a real-time decision-making optimization problem (RDOP) by leveraging Lyapunov optimization. Then, to solve the RDOP, we introduce an online learning-based latency prediction method to predict the uncertain system environment and a game theoretic decision-making method to make real-time decisions. Finally, theoretical analysis confirms the effectiveness of the ODOA. Simulation results show that the proposed ODOA outperforms various benchmark approaches and improves the QoS of ISDs by at least 14.5% compared to deep reinforcement learning (DRL)-based approaches, thereby validating the superiority of the proposed approach.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 3","pages":"4363-4380"},"PeriodicalIF":9.2,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146116875","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 : 2025-10-22DOI: 10.1109/TMC.2025.3624064
Dongping Liao;Xitong Gao;Chengzhong Xu
Federated learning (FL) enables collaborative training on decentralized data while preserving the data owners’ privacy, under the orchestration of a central server. FL has seen tremendous growth and advancements in recent years. Despite its progress, FL faces a significant challenge raised by data heterogeneity, leading to a slower convergence rate and a larger performance gap compared to centralized training. In this work, we empirically reveal that direct applying empirical risk minimizing (ERM) on skewed client training data causes the client model suffers from biased predictions towards majority classes. To address this problem, we propose a model agnostic instance reweighing method (MAIR). At a coarse-grained level, MAIR adjusts the logits predictions for each class to counteract the data heterogeneity. At a fine-grained level, it dynamically reweighs the importance of individual training samples with a predictive meta network. As a results, MAIR prevents client models from over-fitting on heterogeneous data and therefore substantially reduces client drift. Theoretically, we justify its non-convex convergence property. Extensive experiments demonstrate that MAIR reliably speeds up convergence and improves the quality of global models, outperforming its best competitor by a clear margin. It notably delivers $8.3%$ improvements on ImageNet subset and achieves $67.6%$ energy footprint reduction on CIFAR-100 over the FedAvg baseline. Our findings also suggest that improving the performance of FL-trained models necessitates rethinking clients’ local optimization objectives, and ERM should thus no longer be viewed as a de facto standard in FL under data heterogeneity.
{"title":"MAIR: Model Agnostic Instance Reweighing for Heterogeneous Federated Learning","authors":"Dongping Liao;Xitong Gao;Chengzhong Xu","doi":"10.1109/TMC.2025.3624064","DOIUrl":"https://doi.org/10.1109/TMC.2025.3624064","url":null,"abstract":"Federated learning (FL) enables collaborative training on decentralized data while preserving the data owners’ privacy, under the orchestration of a central server. FL has seen tremendous growth and advancements in recent years. Despite its progress, FL faces a significant challenge raised by data heterogeneity, leading to a slower convergence rate and a larger performance gap compared to centralized training. In this work, we empirically reveal that direct applying empirical risk minimizing (ERM) on skewed client training data causes the client model suffers from biased predictions towards majority classes. To address this problem, we propose a model agnostic instance reweighing method (MAIR). At a coarse-grained level, MAIR adjusts the logits predictions for each class to counteract the data heterogeneity. At a fine-grained level, it dynamically reweighs the importance of individual training samples with a predictive meta network. As a results, MAIR prevents client models from over-fitting on heterogeneous data and therefore substantially reduces client drift. Theoretically, we justify its non-convex convergence property. Extensive experiments demonstrate that MAIR reliably speeds up convergence and improves the quality of global models, outperforming its best competitor by a clear margin. It notably delivers <inline-formula><tex-math>$8.3%$</tex-math></inline-formula> improvements on ImageNet subset and achieves <inline-formula><tex-math>$67.6%$</tex-math></inline-formula> energy footprint reduction on CIFAR-100 over the FedAvg baseline. Our findings also suggest that improving the performance of FL-trained models necessitates rethinking clients’ local optimization objectives, and ERM should thus no longer be viewed as a de facto standard in FL under data heterogeneity.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 3","pages":"4241-4252"},"PeriodicalIF":9.2,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146116913","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：