Pub Date : 2024-10-04DOI: 10.1109/TMC.2024.3474671
Jie Wang;Jingmiao Wu;Yingwei Qu;Qi Xiao;Qinghua Gao;Yuguang Fang
Device-free positioning (DFP) using mmWave signals is an emerging technique that could track a target without attaching any devices. It conducts position estimation by analyzing the influence of targets on their surrounding mmWave signals. With the widespread utilization of mmWave signals, DFP will have many potential applications in tracking pedestrians and robots in intelligent monitoring systems. State-of-the-art DFP work has already achieved excellent positioning performance when there is one target only, but when there are multiple targets, the time-varying target state, such as entering or leaving of the wireless coverage area and close interactions, makes it challenging to track every target. To solve these problems, in this paper, we propose a spatial-temporal analysis method to robustly track multiple targets based on the high precision mmWave point cloud information. Specifically, we propose a high precision spatial imaging strategy to construct fine-grained mmWave point cloud of the targets, design a spatial-temporal point cloud clustering method to determine the target state, and then leverage a gait based identity and trajectory association scheme and a particle filter to achieve robust identity-aware tracking. Extensive evaluations on a 77 GHz mmWave testbed have been conducted to demonstrate the effectiveness and robustness of our proposed schemes.
{"title":"Multi-Target Device-Free Positioning Based on Spatial-Temporal mmWave Point Cloud","authors":"Jie Wang;Jingmiao Wu;Yingwei Qu;Qi Xiao;Qinghua Gao;Yuguang Fang","doi":"10.1109/TMC.2024.3474671","DOIUrl":"https://doi.org/10.1109/TMC.2024.3474671","url":null,"abstract":"Device-free positioning (DFP) using mmWave signals is an emerging technique that could track a target without attaching any devices. It conducts position estimation by analyzing the influence of targets on their surrounding mmWave signals. With the widespread utilization of mmWave signals, DFP will have many potential applications in tracking pedestrians and robots in intelligent monitoring systems. State-of-the-art DFP work has already achieved excellent positioning performance when there is one target only, but when there are multiple targets, the time-varying target state, such as entering or leaving of the wireless coverage area and close interactions, makes it challenging to track every target. To solve these problems, in this paper, we propose a spatial-temporal analysis method to robustly track multiple targets based on the high precision mmWave point cloud information. Specifically, we propose a high precision spatial imaging strategy to construct fine-grained mmWave point cloud of the targets, design a spatial-temporal point cloud clustering method to determine the target state, and then leverage a gait based identity and trajectory association scheme and a particle filter to achieve robust identity-aware tracking. Extensive evaluations on a 77 GHz mmWave testbed have been conducted to demonstrate the effectiveness and robustness of our proposed schemes.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1163-1180"},"PeriodicalIF":7.7,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938441","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 : 2024-10-04DOI: 10.1109/TMC.2024.3474673
Long Huang;Chen Wang
Biometrics have been widely applied for user authentication. However, existing biometric authentications are vulnerable to biometric spoofing, because they can be observed and forged. In addition, they rely on verifying biometric features that rarely change. To address this issue, we propose to verify the handgrip biometric that can be unobtrusively extracted by acoustic signals when the user holds the phone. This biometric is uniquely associated with the user’s hand geometry, body-fat ratio, and gripping strength, which are hard to reproduce. Furthermore, we propose two biometric encoding techniques (i.e., temporal-frequential and spatial) to convert static biometrics into dynamic biometric features to prevent data reuse. In particular, we develop a biometric authentication system to work with the challenge-response protocol. We encode the ultrasonic signal according to a random challenge sequence and extract a distinct biometric code as the response. We further develop two decoding algorithms to decode the biometric code for user authentication. Additionally, we investigate multiple new attacks and explore using a latent diffusion model to solve the acoustic noise discrepancies between the training and testing data to improve system performance. Extensive experiments show our system achieves 97% accuracy in distinguishing users and rejects 100% replay attacks with $ 0.6 , s$ challenge sequence.
{"title":"Biometric Encoding for Replay-Resistant Smartphone User Authentication Using Handgrips","authors":"Long Huang;Chen Wang","doi":"10.1109/TMC.2024.3474673","DOIUrl":"https://doi.org/10.1109/TMC.2024.3474673","url":null,"abstract":"Biometrics have been widely applied for user authentication. However, existing biometric authentications are vulnerable to biometric spoofing, because they can be observed and forged. In addition, they rely on verifying biometric features that rarely change. To address this issue, we propose to verify the handgrip biometric that can be unobtrusively extracted by acoustic signals when the user holds the phone. This biometric is uniquely associated with the user’s hand geometry, body-fat ratio, and gripping strength, which are hard to reproduce. Furthermore, we propose two biometric encoding techniques (i.e., temporal-frequential and spatial) to convert static biometrics into dynamic biometric features to prevent data reuse. In particular, we develop a biometric authentication system to work with the challenge-response protocol. We encode the ultrasonic signal according to a random challenge sequence and extract a distinct biometric code as the response. We further develop two decoding algorithms to decode the biometric code for user authentication. Additionally, we investigate multiple new attacks and explore using a latent diffusion model to solve the acoustic noise discrepancies between the training and testing data to improve system performance. Extensive experiments show our system achieves 97% accuracy in distinguishing users and rejects 100% replay attacks with \u0000<inline-formula><tex-math>$ 0.6 , s$</tex-math></inline-formula>\u0000 challenge sequence.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1230-1248"},"PeriodicalIF":7.7,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938387","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 : 2024-10-04DOI: 10.1109/TMC.2024.3474743
Zhiqiang Cao;Yun Cheng;Zimu Zhou;Yongrui Chen;Youbing Hu;Anqi Lu;Jie Liu;Zhijun Li
Object detection, a fundamental task in computer vision, is crucial for various intelligent edge computing applications. However, object detection algorithms are usually heavy in computation, hindering their deployments on resource-constrained edge devices. Traditional edge-cloud collaboration schemes, like deep neural network (DNN) partitioning across edge and cloud, are unfit for object detection due to the significant communication costs incurred by the large size of intermediate results. To this end, we propose a Difficult-Case based Small-Big model (DCSB) framework. It employs a difficult-case discriminator on the edge device to control data transfer between the small model on the edge and the large model in the cloud. We also adopt regional sampling to further reduce the bandwidth consumption and create a discriminator zoo to accommodate the varying networking conditions. Additionally, we extend DCSB to video tasks by developing an adaptive sampling rate update algorithm, aiming to minimize computational demands without sacrificing detection accuracy. Extensive experiments show that DCSB can detect 97.26%-97.96% objects while saving 74.37%-82.23% network bandwidth, compared to cloud-only methods. Furthermore, DCSB significantly outperforms the latest DNN partitioning methods, reducing inference time by 92.60%-95.10% given an 8Mbps transmission bandwidth. In video tasks, DCSB matches the detection accuracy of leading video analysis methods while cutting the computational overhead by 40%.
{"title":"Edge-Cloud Collaborated Object Detection via Bandwidth Adaptive Difficult-Case Discriminator","authors":"Zhiqiang Cao;Yun Cheng;Zimu Zhou;Yongrui Chen;Youbing Hu;Anqi Lu;Jie Liu;Zhijun Li","doi":"10.1109/TMC.2024.3474743","DOIUrl":"https://doi.org/10.1109/TMC.2024.3474743","url":null,"abstract":"Object detection, a fundamental task in computer vision, is crucial for various intelligent edge computing applications. However, object detection algorithms are usually heavy in computation, hindering their deployments on resource-constrained edge devices. Traditional edge-cloud collaboration schemes, like deep neural network (DNN) partitioning across edge and cloud, are unfit for object detection due to the significant communication costs incurred by the large size of intermediate results. To this end, we propose a Difficult-Case based Small-Big model (DCSB) framework. It employs a difficult-case discriminator on the edge device to control data transfer between the small model on the edge and the large model in the cloud. We also adopt regional sampling to further reduce the bandwidth consumption and create a discriminator zoo to accommodate the varying networking conditions. Additionally, we extend DCSB to video tasks by developing an adaptive sampling rate update algorithm, aiming to minimize computational demands without sacrificing detection accuracy. Extensive experiments show that DCSB can detect 97.26%-97.96% objects while saving 74.37%-82.23% network bandwidth, compared to cloud-only methods. Furthermore, DCSB significantly outperforms the latest DNN partitioning methods, reducing inference time by 92.60%-95.10% given an 8Mbps transmission bandwidth. In video tasks, DCSB matches the detection accuracy of leading video analysis methods while cutting the computational overhead by 40%.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1181-1196"},"PeriodicalIF":7.7,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938442","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 : 2024-10-04DOI: 10.1109/TMC.2024.3474732
Qi Guo;Di Wu;Yong Qi;Saiyu Qi
Federated semi-supervised learning (FSSL), facilitates labeled clients and unlabeled clients jointly training a global model without sharing private data. Existing FSSL methods predominantly employ pseudo-labeling and consistency regularization to exploit the knowledge of unlabeled data, achieving notable success in raw data utilization. However, the effectiveness of these methods is challenged by large deviations between uploaded local models of labeled and unlabeled clients, as well as confirmation bias introduced by noisy pseudo-labels, both of which negatively affect the global model's performance. In this paper, we present a novel FSSL method called Dual Class-aware Contrastive Federated Semi-Supervised Learning (DCCFSSL). This method considers both the local class-aware distribution of each client's data and the global class-aware distribution of all clients’ data within the feature space. By implementing a dual class-aware contrastive module, DCCFSSL establishes a unified training objective for different clients to tackle large deviations and incorporates contrastive information in the feature space to mitigate confirmation bias. Additionally, DCCFSSL introduces an authentication-reweighted aggregation technique to improve the server's aggregation robustness. Our comprehensive experiments show that DCCFSSL outperforms current state-of-the-art methods on three benchmark datasets and surpasses the FedAvg with relabeled unlabeled clients on CIFAR-10, CIFAR-100, and STL-10 datasets.
{"title":"Dual Class-Aware Contrastive Federated Semi-Supervised Learning","authors":"Qi Guo;Di Wu;Yong Qi;Saiyu Qi","doi":"10.1109/TMC.2024.3474732","DOIUrl":"https://doi.org/10.1109/TMC.2024.3474732","url":null,"abstract":"Federated semi-supervised learning (FSSL), facilitates labeled clients and unlabeled clients jointly training a global model without sharing private data. Existing FSSL methods predominantly employ pseudo-labeling and consistency regularization to exploit the knowledge of unlabeled data, achieving notable success in raw data utilization. However, the effectiveness of these methods is challenged by large deviations between uploaded local models of labeled and unlabeled clients, as well as confirmation bias introduced by noisy pseudo-labels, both of which negatively affect the global model's performance. In this paper, we present a novel FSSL method called Dual Class-aware Contrastive Federated Semi-Supervised Learning (DCCFSSL). This method considers both the local class-aware distribution of each client's data and the global class-aware distribution of all clients’ data within the feature space. By implementing a dual class-aware contrastive module, DCCFSSL establishes a unified training objective for different clients to tackle large deviations and incorporates contrastive information in the feature space to mitigate confirmation bias. Additionally, DCCFSSL introduces an authentication-reweighted aggregation technique to improve the server's aggregation robustness. Our comprehensive experiments show that DCCFSSL outperforms current state-of-the-art methods on three benchmark datasets and surpasses the FedAvg with relabeled unlabeled clients on CIFAR-10, CIFAR-100, and STL-10 datasets.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1073-1089"},"PeriodicalIF":7.7,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938598","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 : 2024-10-03DOI: 10.1109/TMC.2024.3473908
Boyi Tang;Yijun Mo;Chen Yu;Huiyu Liu
Network slicing has become a primary function of 5G/6G network resource management. However, the existing slicing schemes have not sufficiently discussed the reconfiguration optimization schemes brought by user behavior changes and mobile network environment fluctuations, leading to excessive service interruption rates and slice reconfiguration costs in dynamic environments. To address this problem, this paper proposes an End-to-end Steady-state Adaptive slicing method for Dynamic network state and load (ESAD). To realize the steady-state slicing decisions, ESAD takes the steady-state degree of network slicing and reconfiguration cost as the objective and constructs the slicing reconfiguration probability evaluation function based on the service load dynamics function and the time-varying function of the network channel conditions. To improve the predictability and steady-state degree of the slicing decision, ESAD introduces an ensemble deep learning method to predict the load service fluctuation based on the user behavior model and employs reinforcement learning to compute the channel dynamics boundary, which guides the slicing decision to balance the network dynamics factors. Experiments on quality of service assurance for 5G cloud game rendering class prove that ESAD can reduce reconfiguration probability and long-term reconfiguration cost by 49.45%–58.50% while improving system QoS assurance and capacity.
{"title":"End-to-End Steady-State Adaptive Slicing Method for Dynamic Network State and Load","authors":"Boyi Tang;Yijun Mo;Chen Yu;Huiyu Liu","doi":"10.1109/TMC.2024.3473908","DOIUrl":"https://doi.org/10.1109/TMC.2024.3473908","url":null,"abstract":"Network slicing has become a primary function of 5G/6G network resource management. However, the existing slicing schemes have not sufficiently discussed the reconfiguration optimization schemes brought by user behavior changes and mobile network environment fluctuations, leading to excessive service interruption rates and slice reconfiguration costs in dynamic environments. To address this problem, this paper proposes an End-to-end Steady-state Adaptive slicing method for Dynamic network state and load (ESAD). To realize the steady-state slicing decisions, ESAD takes the steady-state degree of network slicing and reconfiguration cost as the objective and constructs the slicing reconfiguration probability evaluation function based on the service load dynamics function and the time-varying function of the network channel conditions. To improve the predictability and steady-state degree of the slicing decision, ESAD introduces an ensemble deep learning method to predict the load service fluctuation based on the user behavior model and employs reinforcement learning to compute the channel dynamics boundary, which guides the slicing decision to balance the network dynamics factors. Experiments on quality of service assurance for 5G cloud game rendering class prove that ESAD can reduce reconfiguration probability and long-term reconfiguration cost by 49.45%–58.50% while improving system QoS assurance and capacity.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1090-1104"},"PeriodicalIF":7.7,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938400","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 : 2024-10-03DOI: 10.1109/TMC.2024.3472898
Xin Wang;Yanhan Wang;Ming Yang;Feng Li;Xiaoming Wu;Lisheng Fan;Shibo He
Federated learning (FL) is an effective mobile edge computing framework that enables multiple participants to collaboratively train intelligent models, without requiring large amounts of data transmission while protecting privacy. However, FL encounters challenges due to non-independent and identically distributed (non-IID) data from different participants. The existing methods, whether focusing on local training or global aggregation, often suffer from insufficient unilateral optimization. Achieving effective local-global collaborative optimization, particularly in the absence of additional reference models or datasets, is both crucial and challenging. To address this, we propose a novel approach: D ual- A ggregated Fed erated learning based on a triple Siam ese network ( FedSiam-DA ). This method enhances the FL algorithm on both client and server sides. On the client side, we establish a triple Siamese network incorporating a stop-gradient scheme, which leverages a contrastive learning strategy to control the update directions of local models. On the server side, we introduce a dual aggregation mechanism with dynamic weights for local updates, improving the global model’s ability to assimilate personalized knowledge from local models. Extensive experiments on multiple benchmark datasets demonstrate that FedSiam-DA significantly improves model performance under non-IID data conditions compared to existing methods.
{"title":"FedSiam-DA: Dual-Aggregated Federated Learning via Siamese Network for Non-IID Data","authors":"Xin Wang;Yanhan Wang;Ming Yang;Feng Li;Xiaoming Wu;Lisheng Fan;Shibo He","doi":"10.1109/TMC.2024.3472898","DOIUrl":"https://doi.org/10.1109/TMC.2024.3472898","url":null,"abstract":"Federated learning (FL) is an effective mobile edge computing framework that enables multiple participants to collaboratively train intelligent models, without requiring large amounts of data transmission while protecting privacy. However, FL encounters challenges due to non-independent and identically distributed (non-IID) data from different participants. The existing methods, whether focusing on local training or global aggregation, often suffer from insufficient unilateral optimization. Achieving effective local-global collaborative optimization, particularly in the absence of additional reference models or datasets, is both crucial and challenging. To address this, we propose a novel approach: \u0000<bold>D</b>\u0000ual-\u0000<bold>A</b>\u0000ggregated \u0000<bold>Fed</b>\u0000erated learning based on a triple \u0000<bold>Siam</b>\u0000ese network (\u0000<bold>FedSiam-DA</b>\u0000). This method enhances the FL algorithm on both client and server sides. On the client side, we establish a triple Siamese network incorporating a stop-gradient scheme, which leverages a contrastive learning strategy to control the update directions of local models. On the server side, we introduce a dual aggregation mechanism with dynamic weights for local updates, improving the global model’s ability to assimilate personalized knowledge from local models. Extensive experiments on multiple benchmark datasets demonstrate that FedSiam-DA significantly improves model performance under non-IID data conditions compared to existing methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"985-998"},"PeriodicalIF":7.7,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938594","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 : 2024-10-02DOI: 10.1109/TMC.2024.3472643
Rong Fan;Azzedine Boukerche;Pan Pan;Zhigang Jin;Yishan Su;Fei Dou
In harsh underwater environments, the localization of network nodes faces severe challenges due to open deployment environments. Most existing underwater localization methods suffer from privacy leaks. However, privacy protection schemes applied in terrestrial networks are not viable for underwater acoustic networks due to stratification effects and multipath complexities. In this paper, we introduce a secure localization scheme for underwater wireless sensor networks (UWSNs) utilizing cooperative beamforming among mobile underwater anchor nodes. With this scheme, the underwater sensor communicates and ranges with mobile anchor nodes to perform self-localization via time difference of arrival (TDOA) algorithm. However, the presence of eavesdroppers poses a threat by intercepting information emitted by the anchors. To avoid localization information leakage, then we model the secure localization requirement as a multi-anchors multi-objective dual joint optimization problem to enhance both security and energy performance. The deep reinforcement learning (DRL)-based multi-agent deep deterministic policy gradient (MADDPG) algorithm is applied to solve the optimization problem. Both simulation and field experimental results robustly validate the efficiency and accuracy of the proposed secure localization scheme.
{"title":"Secure Localization for Underwater Wireless Sensor Networks via AUV Cooperative Beamforming With Reinforcement Learning","authors":"Rong Fan;Azzedine Boukerche;Pan Pan;Zhigang Jin;Yishan Su;Fei Dou","doi":"10.1109/TMC.2024.3472643","DOIUrl":"https://doi.org/10.1109/TMC.2024.3472643","url":null,"abstract":"In harsh underwater environments, the localization of network nodes faces severe challenges due to open deployment environments. Most existing underwater localization methods suffer from privacy leaks. However, privacy protection schemes applied in terrestrial networks are not viable for underwater acoustic networks due to stratification effects and multipath complexities. In this paper, we introduce a secure localization scheme for underwater wireless sensor networks (UWSNs) utilizing cooperative beamforming among mobile underwater anchor nodes. With this scheme, the underwater sensor communicates and ranges with mobile anchor nodes to perform self-localization via time difference of arrival (TDOA) algorithm. However, the presence of eavesdroppers poses a threat by intercepting information emitted by the anchors. To avoid localization information leakage, then we model the secure localization requirement as a multi-anchors multi-objective dual joint optimization problem to enhance both security and energy performance. The deep reinforcement learning (DRL)-based multi-agent deep deterministic policy gradient (MADDPG) algorithm is applied to solve the optimization problem. Both simulation and field experimental results robustly validate the efficiency and accuracy of the proposed secure localization scheme.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"924-938"},"PeriodicalIF":7.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938588","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}
Mobility scooters serve as a powerful last-mile transportation tool for people with mobility challenges. Given the unique riding behavior and posture of mobility scooter riders, such user-specific mobility scooter ride data has tremendous potential towards the design of continuous user identification and authentication mechanisms. However, there have been no prior research efforts in the literature exploring this unique modality for the design of continuous user identification techniques. To address this gap, this paper proposes ScooterID , the first framework which employs rider posture data collected from cameras on mobility scooters to continuously identify (and authenticate) users/riders. As part of this framework, a machine learning based model comprising of a spatio-temporal Graph Convolutional Network and a body-part-informed encoder is designed to effectively capture a user’s subtle upper-body movements during mobility scooter rides into discriminating embedding vectors. These embeddings can then be used to reliably and continuously identify and authenticate users/riders. Experiments with real-world mobility scooter ride data show that ScooterID achieves high levels of authentication accuracy with few enrollment video samples. ScooterID also performs efficiently on resource-constrained devices (e.g., Raspberry Pis) and is robust against adversarial perturbations to authentication inputs.
{"title":"ScooterID: Posture-Based Continuous User Identification From Mobility Scooter Rides","authors":"Devan Shah;Ruoqi Huang;Nisha Vinayaga-Sureshkanth;Tingting Chen;Murtuza Jadliwala","doi":"10.1109/TMC.2024.3473609","DOIUrl":"https://doi.org/10.1109/TMC.2024.3473609","url":null,"abstract":"Mobility scooters serve as a powerful last-mile transportation tool for people with mobility challenges. Given the unique riding behavior and posture of mobility scooter riders, such user-specific mobility scooter ride data has tremendous potential towards the design of continuous user identification and authentication mechanisms. However, there have been no prior research efforts in the literature exploring this unique modality for the design of continuous user identification techniques. To address this gap, this paper proposes \u0000<italic>ScooterID</i>\u0000, the first framework which employs rider posture data collected from cameras on mobility scooters to continuously identify (and authenticate) users/riders. As part of this framework, a machine learning based model comprising of a spatio-temporal Graph Convolutional Network and a body-part-informed encoder is designed to effectively capture a user’s subtle upper-body movements during mobility scooter rides into discriminating embedding vectors. These embeddings can then be used to reliably and continuously identify and authenticate users/riders. Experiments with real-world mobility scooter ride data show that \u0000<italic>ScooterID</i>\u0000 achieves high levels of authentication accuracy with few enrollment video samples. \u0000<italic>ScooterID</i>\u0000 also performs efficiently on resource-constrained devices (e.g., Raspberry Pis) and is robust against adversarial perturbations to authentication inputs.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"970-984"},"PeriodicalIF":7.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938592","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 : 2024-10-01DOI: 10.1109/TMC.2024.3470339
Yi Wu;Xiande Zhang;Tianhao Wu;Bing Zhou;Phuc Nguyen;Jian Liu
Facial landmark tracking and 3D reconstruction have gained considerable attention due to their numerous applications such as human-computer interactions, facial expression analysis, and emotion recognition, etc. Traditional approaches require users to be confined to a particular location and face a camera under constrained recording conditions, which prevents them from being deployed in many application scenarios involving human motions. In this paper, we propose the first single-earpiece lightweight biosensing system, BioFace-3D , that can unobtrusively, continuously, and reliably sense the entire facial movements, track 2D facial landmarks, and further render 3D facial animations. Our single-earpiece biosensing system takes advantage of the cross-modal transfer learning model to transfer the knowledge embodied in a high-grade visual facial landmark detection model to the low-grade biosignal domain. After training, our BioFace-3D can directly perform continuous 3D facial reconstruction from the biosignals, without any visual input. Additionally, by utilizing biosensors, we also showcase the potential for capturing both behavioral aspects, such as facial gestures, and distinctive individual physiological traits, establishing a comprehensive two-factor authentication/identification framework. Extensive experiments involving 16 participants demonstrate that BioFace-3D can accurately track 53 major facial landmarks with only 1.85 mm average error and 3.38% normalized mean error, which is comparable with most state-of-the-art camera-based solutions. Experiments also show that the system can authenticate users with high accuracy (e.g., over 99.8% within two trials for three gestures in series), low false positive rate (e.g., less 0.24%), and is robust to various types of attacks.
{"title":"3D Facial Tracking and User Authentication Through Lightweight Single-Ear Biosensors","authors":"Yi Wu;Xiande Zhang;Tianhao Wu;Bing Zhou;Phuc Nguyen;Jian Liu","doi":"10.1109/TMC.2024.3470339","DOIUrl":"https://doi.org/10.1109/TMC.2024.3470339","url":null,"abstract":"Facial landmark tracking and 3D reconstruction have gained considerable attention due to their numerous applications such as human-computer interactions, facial expression analysis, and emotion recognition, etc. Traditional approaches require users to be confined to a particular location and face a camera under constrained recording conditions, which prevents them from being deployed in many application scenarios involving human motions. In this paper, we propose the first single-earpiece lightweight biosensing system, \u0000<italic>BioFace-3D</i>\u0000, that can unobtrusively, continuously, and reliably sense the entire facial movements, track 2D facial landmarks, and further render 3D facial animations. Our single-earpiece biosensing system takes advantage of the cross-modal transfer learning model to transfer the knowledge embodied in a \u0000<italic>high-grade</i>\u0000 visual facial landmark detection model to the \u0000<italic>low-grade</i>\u0000 biosignal domain. After training, our \u0000<italic>BioFace-3D</i>\u0000 can directly perform continuous 3D facial reconstruction from the biosignals, without any visual input. Additionally, by utilizing biosensors, we also showcase the potential for capturing both behavioral aspects, such as facial gestures, and distinctive individual physiological traits, establishing a comprehensive two-factor authentication/identification framework. Extensive experiments involving 16 participants demonstrate that \u0000<italic>BioFace-3D</i>\u0000 can accurately track 53 major facial landmarks with only 1.85 mm average error and 3.38% normalized mean error, which is comparable with most state-of-the-art camera-based solutions. Experiments also show that the system can authenticate users with high accuracy (e.g., over 99.8% within two trials for three gestures in series), low false positive rate (e.g., less 0.24%), and is robust to various types of attacks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"749-762"},"PeriodicalIF":7.7,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938471","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 : 2024-09-30DOI: 10.1109/TMC.2024.3471569
Qihang Zhou;Xinglin Zhang;Zheng Yang
Many mobile crowdsensing applications require efficient recruitment of workers whose qualities are often unknown a priori. While prior research has explored multi-armed bandit-based mechanisms with short-term incentives to address this unknown worker recruitment challenge, these mechanisms mostly neglect the enduring participation issues stemming from privacy concern and selection starvation in the long-term task. Therefore, in this paper, we focus on incentivizing long-term participation of unknown workers, thereby providing crucial assurance for crowdsensing applications. We first establish an auction framework based on shuffle differential privacy (SDP), where we leverage SDP’s privacy amplification effect to mitigate privacy-related utility loss when dealing with the privacy-sensitive worker and the utility-sensitive platform. Following this, we model the selection requirements of workers as fairness constraints and propose two novel fairness-aware incentive mechanisms, GFA and IFA, to ensure group and individual fairness for unknown workers, respectively. Theoretical analyses highlight the desirable properties of GFA and IFA, complemented by an in-depth exploration of fairness violation and regret. Finally, numerical simulations are conducted on two real-world datasets, validating the superior performance of the proposed mechanisms.
{"title":"Unknown Worker Recruitment With Long-Term Incentive in Mobile Crowdsensing","authors":"Qihang Zhou;Xinglin Zhang;Zheng Yang","doi":"10.1109/TMC.2024.3471569","DOIUrl":"https://doi.org/10.1109/TMC.2024.3471569","url":null,"abstract":"Many mobile crowdsensing applications require efficient recruitment of workers whose qualities are often unknown a priori. While prior research has explored multi-armed bandit-based mechanisms with short-term incentives to address this unknown worker recruitment challenge, these mechanisms mostly neglect the enduring participation issues stemming from privacy concern and selection starvation in the long-term task. Therefore, in this paper, we focus on incentivizing long-term participation of unknown workers, thereby providing crucial assurance for crowdsensing applications. We first establish an auction framework based on shuffle differential privacy (SDP), where we leverage SDP’s privacy amplification effect to mitigate privacy-related utility loss when dealing with the privacy-sensitive worker and the utility-sensitive platform. Following this, we model the selection requirements of workers as fairness constraints and propose two novel fairness-aware incentive mechanisms, GFA and IFA, to ensure group and individual fairness for unknown workers, respectively. Theoretical analyses highlight the desirable properties of GFA and IFA, complemented by an in-depth exploration of fairness violation and regret. Finally, numerical simulations are conducted on two real-world datasets, validating the superior performance of the proposed mechanisms.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"999-1015"},"PeriodicalIF":7.7,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938591","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：