检索结果-内蒙古大学图书馆

ShieldTSE: A Privacy-Enhanced Split Federated Learning Framework for Traffic State Estimation in IoV

IEEE INTERNET OF THINGS JOURNAL 2024年第22期11卷 37324-37339页

作者： Chen, Tong Bai, Xiaoshan Zhao, Jiejie Wang, Haiquan Du, Bowen Li, Lei Zhang, Shan Beihang Univ State Key Lab Complex & Crit Software Environm Beijing 100191 Peoples R China Beihang Univ Sch Software Beijing 100191 Peoples R China Zhongguancun Lab Beijing 100191 Peoples R China Beihang Univ State Key Lab Complex & Crit Software Environm Zhongguancun Lab Beijing 100191 Peoples R China Beihang Univ Sch Transportat Sci & Engn Beijing 100191 Peoples R China Beihang Univ Sch Comp Sci & Engn Zhongguancun Lab Beijing 100191 Peoples R China

Traffic state estimation (TSE) is attracting significant attention due to its importance to the Internet of Vehicles (IoV) for various applications, such as vehicle path planning. In classic IoV, the real-time traffic data collected by road side units requires transferring to the cloud server for processing. Such a centralized manner may raise privacy leakage issues. Split federated learning (SFL) has emerged as one of the prevalent methods to solve these issues. However, recent studies have shown that the existing SFL frameworks are vulnerable to the model inversion (MI) attacks, leading to private raw data leakage. To this end, in this article, we propose ShieldTSE, a privacy-enhanced SFL framework for TSE in IoV. To protect privacy and maintain utility, a variational encoder-decoder-based privacy-preserving feature extraction module with adversarial learning is first proposed to generate better privacy-preserved intermediate activations with a lower-dimensional feature space. Then, a hard attention-based feature selection module is designed to select partial yet crucial features from the intermediate activations by removing redundant sensitive features to further reduce the data privacy leakage. Experimental results demonstrate that ShieldTSE achieves superior privacy-preserving ability when against training-based and optimization-based MI attacks with an average reconstruction mean-square error (MSE) improvement of 18x and 35x on METR-LA and PEMS-BAY compared to the baseline without the privacy-preserving strategy, respectively. ShieldTSE also successfully maintains better model utility compared to the privacy protection baselines.

关键词： Servers Data models Privacy Data privacy Federated learning distributed databases State estimation graph neural networks (GNNs) split federated learning (SFL) traffic state estimation (TSE)

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Robust distributed Online Learning: Taming Adversarial Participants in An Adversarial Environment

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2024年 72卷 235-248页

作者： Dong, Xingrong Wu, Zhaoxian Ling, Qing Tian, Zhi Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China Sch Comp Sci & Engn Peng Cheng Lab Shenzhen 518066 Guangdong Peoples R China George Mason Univ Dept Elect & Comp Engn Fairfax VA 22030 USA

This paper studies distributed online learning under Byzantine attacks. The performance of an online learning algorithm is often characterized by (adversarial) regret, which evaluates the quality of one-step-ahead decision-making when an environment incurs adversarial losses, and a sublinear regret bound is preferred. But we prove that, even with a class of state-of-the-art robust aggregation rules, in an adversarial environment and in the presence of Byzantine participants, distributed online gradient descent can only achieve a linear adversarial regret bound, which is tight. This is the inevitable consequence of Byzantine attacks, even though we can control the constant of the linear adversarial regret to a reasonable level. Interestingly, when the environment is not fully adversarial so that the losses of the honest participants are i.i.d. (independent and identically distributed), we show that sublinear stochastic regret, in contrast to the aforementioned adversarial regret, is possible. We develop Byzantine-robust distributed online momentum algorithms to attain such sublinear stochastic regret bounds for a class of robust aggregation rules. Numerical experiments corroborate our theoretical analysis.

关键词： distributed databases distributed optimization Byzantine-robustness online learning

来源：评论

学校读者我要写书评

暂无评论

SAM: An Efficient Approach With Selective Aggregation of Models in Federated Learning

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第11期11卷 20769-20783页

作者： Shi, Yuchen Fan, Pingyi Zhu, Zheqi Peng, Chenghui Wang, Fei Letaief, Khaled B. Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Huawei Technol Wireless Technol Lab Shanghai 201206 Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China

Federated learning (FL) is a promising distributed learning mechanism that revolutionizes our interaction with data in the IoT ecosystem. Due to the rapidly growing scale of smart devices and the limited transmission resources of networks, a simple, consistent, and scalable FL framework aiming to address the communication bottleneck is urgently needed. In this work, we propose an efficient approach with selective aggregation of models (SAMs) to mitigate the communication overload in FL systems. The introduction of SAM enables each local client to upload its model with a certain probability, resulting in a significant reduction in costly communication expenses. We design the algorithm for SAM, analyze the convergence bound on nonconvex objectives for heterogeneous data, which illustrates the impact of the selection probability as well as the set size of participating clients on the system performance, and assess the conservation for the network resource utilization by modeling queuing systems. We conduct various experiments to evaluate the performance of SAM, whose outcomes suggest that significant alleviation of the communication bottleneck can be accomplished with marginal cost of performance loss. It will also be shown that SAM is a communication-efficient method that can be freely applied to other frameworks.

关键词： Biological system modeling Training Convergence Computational modeling Internet of Things Numerical models distributed databases Communication efficiency federated learning model selection network utilization

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Remote Sensing Image Classification Using Sparse Image Representations

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Kopidaki, Christina Tsagkatakis, Grigorios Tsakalides, Panagiotis Univ Crete Inst Comp Sci Fdn Res & Technol Hellas FORTH Iraklion 70013 Greece Univ Crete Dept Comp Sci Iraklion 70013 Greece

The increasing scale and complexity of remote sensing (RS) observations demand distributed processing to effectively manage the vast volumes of data generated. However, distributed processing presents significant challenges, including bandwidth limitations, high latency, and privacy concerns, especially when transmitting high-resolution images. To address these issues, we propose a novel scheme leveraging the encoder of a masked autoencoder (MAE) to generate associated embedding (CLS tokens) from masked images, which enables training deep learning models under federated learning (FL) scenarios. This approach enables the transmission of compact image patches instead of full images to processing nodes, drastically reducing bandwidth usage. On the processing nodes, classifiers are trained with the CLS tokens, and model weights are aggregated using FedAvg and FedProx FL algorithms. Experimental results on benchmark datasets demonstrate that the proposed approach significantly reduces data transmission requirements while maintaining and even surpassing the accuracy of systems with access to full data.

关键词： Remote sensing Training Servers Data models Bandwidth Federated learning distributed databases Autoencoders Transformers Security Federated learning (FL) masked autoencoders (MAE) remote sensing (RS)

来源：评论

学校读者我要写书评

暂无评论

Weak Moving Target Detection in distributed MIMO Radar With Hybrid Data

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2024年第6期60卷 9291-9306页

作者： Jing, Xinchen Su, Hongtao Li, Ze Yang, Ruixing Zhu, Yuhang Xidian Univ Sch Elect Engn Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China

In this article, we investigate the problem of point-like weak moving target detection in the distributed multiple-input multiple-output (MIMO) radar. Due to limitations in communication bandwidth, data from certain spatially diversity channels (SDCs) necessitate low-bit quantization before transmission to the fusion center, while high-precision echo data from other channels can be utilized directly. The transmission channels are modeled as binary symmetric channels. Given the challenge in obtaining the maximum likelihood estimate of the target complex reflection coefficient, we initially develop a fusion detector applicable to the hybrid data using the Rao criterion, where its asymptotic distribution is also analyzed. Simultaneously, optimizing quantization thresholds for the low-bit quantized SDC using Fisher information as the objective function is conducted to maximize the detection probability. As a crucial aspect of the moving target detection, we examine the problem of target velocity estimate, presenting a maximum likelihood estimator for target velocity and deriving a closed-form Cram & eacute;r-Rao lower bound. Finally, two metrics are designed to characterize the impact of various factors on the performance of the distributed MIMO radar, named as normalized detection probability gain and normalized velocity estimation precision gain, respectively. Simulation results indicate that under high-quality transmission channels, 2-bit quantization yields performance close to optimal. In scenarios of poor channel quality, high-precision echo data help to alleviate the adverse effects of low-bit data on signal fusion when channel distortion occurs.

关键词： MIMO radar Quantization (signal) distributed databases Bandwidth Maximum likelihood estimation Detectors Object detection Cram & eacute r-Rao lower bound (CRLB) distributed multiple-input multiple-output (MIMO) radar maximum likelihood estimate moving target detection Rao test

来源：评论

学校读者我要写书评

暂无评论

Federal Graph Contrastive Learning With Secure Cross-Device Validation

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第12期23卷 14145-14158页

作者： Wang, Tingqi Zheng, Xu Zhang, Jinchuan Tian, Ling Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Sichuan Peoples R China

distributed mobile devices collect unlabeled graph data from environment. Introducing popular graph contrastive learning (GCL) methods can learn node representations better. However, training high-performance GCL requires large-scale data and graph data collected by the single device is insufficient. Meanwhile, transmitting local data for centralized training suffers from non-negotiate privacy leakage and bandwidth consumption. Federated learning (FL), as a distributed learning paradigm, is commonly used for such issues. Nevertheless, direct combination of FL and GCL struggles to supplement global graph information. This absence results in neighbor information missing, thus causing the local GCL to learn biased node representations. Moreover, the combination also triggers potential gradient explosion owing to the lack of unified learning criteria. In this paper, we propose a federal GCL framework that complements missing structural information and provides unified learning criteria. The key idea is to achieve cross-client node alignment on server through local graph structural importance to reason about the global graph information. We design a hierarchical structural importance scoring method to comprehensively evaluate structural importance, thus server performs effective cross-client aggregation while maintaining local graph privacy. We demonstrate the security and prove the bandwidth-reducing advantage of the proposed framework. Extensive experiments on 3 datasets show the superior performance of our method.

关键词： Training Servers Mobile handsets distributed databases Computational modeling Graph neural networks Federated learning distributed knowledge base federated learning graph contrastive learning

来源：评论

学校读者我要写书评

暂无评论

A Robust Framework for Distributional Shift Detection Under Sample-Bias

引用

IEEE ACCESS 2024年 12卷 59598-59611页

作者： Torpmann-Hagen, Birk Riegler, Michael A. Halvorsen, Pal Johansen, Dag UiT Arctic Univ Tromso Inst Comp Sci N-9019 Tromso Norway SimulaMet Dept Holist Syst N-0167 Oslo Norway

Deep Neural Networks have been shown to perform poorly or even fail altogether when deployed in real-world settings, despite exhibiting excellent performance on initial benchmarks. This typically occurs due to relative changes in the nature of the production data, often referred to as distributional shifts. In an attempt to increase the transparency, trustworthiness, and overall utility of deep learning systems, a growing body of work has been dedicated to developing distributional shift detectors. As part of our work, we investigate distributional shift detectors that utilize statistical tests of neural network-based representations of data. We show that these methods are prone to fail under sample-bias, which we argue is unavoidable in most practical machine learning systems. To mitigate this, we implement a novel distributional shift detection framework which explicitly accounts for sample-bias via a simple sample-selection procedure. In particular, we show that the effect of sample-bias can be significantly reduced by performing statistical tests against the most similar data in the training set, as opposed to the training set as a whole. We find that this improves the stability and accuracy of a variety of distributional shift detection methods on both covariate- and semantic-shifts, with improvements to balanced accuracy typically ranging between 0.1 and 0.2, and false-positive-rates often being eliminated altogether under bias.

关键词： Training Data models Training data Detectors Deep learning System performance distributed databases Detection algorithms system support neural networks distributional shift OOD detection sample bias statistical tests

来源：评论

学校读者我要写书评

暂无评论

Federated Synchrophasor Data Prediction, Aggregation and Inference Using Deep Learning: A Case of Proactive Control for Short-Term Stability

引用

IEEE TRANSACTIONS ON POWER DELIVERY 2024年第2期39卷 823-834页

作者： Ahmed, Arman Basumallik, Sagnik Srivastava, Anurag K. Wu, Yinghui Choudhury, Sutanay Washington State Univ Sch Elect Engn & Comp Sci Pullman WA 99163 USA Northwest Natl Lab PNNL Richland WA 99163 USA Pacific Northwest Natl Lab PNNL Intel Senior Artificial Intelligence Algorithm Eng Hillsboro OR 97124 USA West Virginia Univ Comp Sci & Elect Engn Morgantown WV 26506 USA Case Western Reserve Univ Comp & Data Sci Cleveland OH 44106 USA Pacific Northwest Natl Lab Richland WA 99354 USA

A novel asynchronous federated architecture is proposed in this work for data prediction, aggregation, and inference with a use case for fast short-term instability mitigation in transmission systems. Existing machine learning (ML) prediction approaches rely on centralized-schemes that accumulate measurements from distributed regions at a central computing node. This centralized-schemes increase computational overhead leading to prediction delay. Federated-learning collaboratively learns a global model without centralized data processing. Nevertheless, its performance degrades when data becomes non-independent and identically-distributed due to the changes in grid dynamics, leading to expensive model re-training. This research proposes a federated-inference architecture that can exploit data-dependency in different regions to effectively exchange model parameters among high-quality local models and improve local predictive results, hence avoiding the need for global model and re-training effort. The architecture includes several major modules: 1) federated deep ML models using gated-recurrent unit for local synchrophasor data prediction in each region, 2) computationally-efficient data anomaly detection and mitigation using statistical and unsupervised autoencoders, 3) a federated inference algorithm that aggregates model weights and outputs from top-k correlated neighbors to improve local performance, upon system dynamics change, 4) instability prediction and 5) a case analysis for its application in proactive short-term stability control. The efficiency and effectiveness of the proposed approach is validated on modified IEEE test systems with multiple test event scenarios with varying factors, including number of PMUs, error tolerances, and length of input and prediction windows.

关键词： Predictive models Phasor measurement units Power system stability Data models distributed databases Stability criteria Computational modeling Federated inference machine learning short-term stability synchrophasor data unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Winning at the Starting Line: Unreliable Data Replica Selection for Edge Data Integrity Verification

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2024年第6期17卷 4481-4493页

作者： Zhao, Yao Qu, Youyang Xiang, Yong Chen, Feifei Uddin, Md Palash Gao, Longxiang Deakin Univ Sch Informat Technol Burwood Vic 3125 Australia Qilu Univ Technol Minist Educ Shandong Acad Sci Shandong Comp Sci CtrKey Lab Comp Power Network & Jinan 250353 Peoples R China Shandong Fundamental Res Ctr Comp Sci Shandong Prov Key Lab Comp Power Internet & Serv C Jinan 250353 Peoples R China

Mobile Edge Computing (MEC) is an emerging technology, where App vendors are allowed to cache multiple data replicas on geographically distributed edge servers to serve adjacent mobile subscribers. However, this benefit introduces an extra workload for edge servers and App vendors, as they must audit the integrity of multiple data replicas periodically considering various threats caused by distributed and dynamic MEC environments. The large-scale growth of data replicas certainly is a challenge to design more efficient Edge Data Integrity (EDI) verification approaches. Existing solutions are mostly limited to improving efficiency by optimizing proof generation and verification methods, while the improvement is still far from satisfactory due to adopting indiscriminate inspection philosophy (checking all data replicas without discrimination). In this paper, we make the first attempt to abstract a pre-processing phase and correspondingly study the Unreliable data Replica Selection (URS) problem. It can be seamlessly integrated into existing EDI solutions by solving the URS problem at the start of each verification round. Such pre-selection can significantly enhance overall EDI verification efficiency by incorporating the cache service Quality of Service (QoS) and verification success rate, especially in scenarios with a large number of data replicas. Specifically, we first formalize the URS problem as a constrained optimization problem, and further prove its NP -hardness. To address the problem efficiently, we transform it into an easy-to-handle form and develop a Priority-based approach named URS-P. Both theoretical analysis and experimental evaluation validate the effectiveness and efficiency of our proposed solution.

关键词： Quality of service Servers distributed databases Inspection Monitoring Data integrity Optimization Real-time systems Accuracy Vehicle safety Edge data integrity optimization selection algorithm submodular function unreliable data replica

来源：评论

学校读者我要写书评

暂无评论

Omnibus Change Detection in Block Diagonal Covariance Matrix PolSAR Data Illustrated With Simulated and Sentinel-1 Data

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 16359-16376页

作者： Conradsen, Knut Skriver, Henning Nielsen, Allan Aasbjerg Tech Univ Denmark Dept Appl Math & Comp Sci DTU Compute DK-2800 Lyngby Denmark Tech Univ Denmark Natl Space Inst DTU Space DK-2800 Lyngby Denmark

This article describes the latest developments in our work on complex Wishart distribution-based detection of change in time series of multilook polarimetric synthetic aperture radar data in the covariance matrix representation. These developments include better approximations of the probability measures associated with the omnibus test statistics Q and R-} for block diagonal data in general, including the important cases with diagonal only Sentinel-1 data as obtained from Google Earth Engine and reflection symmetry data for full polarimetry. Additionally, the article introduces an omnibus version of the Loewner (or L & ouml;wner) order with visualization of change over time, where the omnibus change path shows significant difference. We also find the time point with the greatest change along the omnibus change path. The processing is illustrated with generated data and a series of 15 Sentinel-1A scenes covering Frankfurt Airport, Germany. Results show that the new and better approximations of the probability measures for the test statistics are important for the assignment of labels "change" or "no change" to a pixel or a patch, especially in "no change" regions. Furthermore, compared to the use of the full covariance matrix, the probability measures associated with the diagonal only test statistics incorrectly detect more change in these "no change" regions for the Sentinel-1 diagonal only data. Hence, the use of the full 2 x 2 covariance matrix if avalable is important. Finally, the omnibus Loewner order gives far fewer false detections than its pairwise counterpart.

关键词： Covariance matrices Synthetic aperture radar Sentinel-1 distributed databases Symbols Speckle Probability distribution Greatest change omnibus likelihood ratio test statistic omnibus Loewner order polarimetric synthetic aperture radar (PolSAR)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：