检索结果-内蒙古大学图书馆

Byzantine-Robust Federated Learning Framework via a Server-Client Defense Mechanisms

IEEE Internet of Things Journal 2025年

作者： Song, Anxiao Zhang, Tao Cheng, Ke Cao, Yang Zhu, Xinghui Shen, Yulong Xidian University School of Computer Science and Technology Xi’an China Shaanxi Key Laboratory of Network and System Security Shaanxi Xi’an710071 China Xidian University School of Computer Science and Technology Shaanxi Xi’an710071 China Xi’an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Shaanxi Xi’an710121 China Institute of Science Tokyo Department of Computer Science Tokyo Japan

Federated Learning (FL), a distributed machine learning (ML) framework, is susceptible to Byzantine attacks since the attacker can manipulate clients' local data or models to compromise the performance of the global model. There has been a wealth of defenses developed to mitigate the attacks by limiting the impact of malicious models. Nevertheless, the attacker can easily circumvent these approaches that rely solely on a single server-side defense, stemming from the high dimensionality of models and the variety of Byzantine attacks. Therefore, we propose Basalt, a Byzantine-robust federated learning framework with a server-client joint defense mechanism that enables multiple clients to train a global ML model under Byzantine attacks. On the client side, we design an efficient self-defense approach with model-level penalty loss that restricts local-benign divergence and decreases local-malicious correlation to prevent misclassification. On the server side, we present an efficient defense strategy based on the manifold and maximum clique, further strengthening the FL's resilience against Byzantine attacks. We provide theoretical guarantees for global model convergence in FL with Byzantine attacks. Our extensive experiments demonstrate that Basalt outperforms existing state-of-the-art works. Especially, it achieves nearly 100% accuracy for detecting malicious clients in nonindependent and nonidentically distributed (Non-IID) MNIST datasets under various Byzantine attacks. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Joint Client Association and Resource Utilizing for Energy-Efficient Semi-Decentralized Federated Learning with Non-IID Data

引用

IEEE Transactions on Wireless Communications 2025年

作者： Zheng, Jiali Yu, Siyi Zhao, Shulin Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Electronics and Information Guangxi Nanning 530004 China

Federated learning (FL), a distributed learning paradigm, has gained widespread application in wireless Internet of Things (IoT) scenarios. To accelerate the convergence of the global model, it is expected to allow more users to participate in the federation for training. However, in heterogeneous scenarios, unrestricted expansion of the FL scale, on the contrary, may reduce the training speed of the FL or even lead to the failure of the model convergence. In this paper, we explore the heterogeneity in wireless networks and propose a semi-decentralized FL architecture that includes a cluster head (CH) selection scheme, as well as resource allocation scheme and device matching method. The selection of the CH is constrained by the minimum overlapping clusters and limited radio resource blocks (RRBs). Additionally, in the resource and device allocation scheme, we reduce overall energy consumption under time constraints while ensuring FL model performance in non-IID environments. To achieve this, we propose a joint optimization problem considering IoT device scheduling and computation frequency allocation. Furthermore, this paper analyzes the low resource efficiency caused by stragglers and proposes a suboptimal solution with lower computational complexity for large-scale applications. Comparisons with several benchmark schemes confirm that our proposed algorithm outperforms them in terms of energy efficiency, model performance, and system stability. © 2002-2012 IEEE.

关键词： non-IID Resource Management and Allocation Semi-Decentralized FL Wireless IoT networks

来源：评论

学校读者我要写书评

暂无评论

PAIR: Complementarity-guided Disentanglement for Composed Image Retrieval

PAIR: Complementarity-guided Disentanglement for Composed Im...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhiheng Fu Zixu Li Zhiwei Chen Chunxiao Wang Xuemeng Song Yupeng Hu Liqiang Nie School of Software Shandong University Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) School of Computer Science and Technology Shandong University School of Computer Science and Technology Harbin Institute of Technology (Shenzhen)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Composed Image Retrieval (CIR) is a novel image retrieval paradigm that aims at searching for the target images via the multimodal query including a reference image and a modification text. Although existing works have made significant progress, they overlook the inter-modal coherence and incoherence relations modeling, hindering the retrieval accuracy of CIR models. This limitation is non-trivial due to the following two challenges: 1) inter-modal incoherence and 2) intra-modal entanglement. To address the above challenges, we propose a comPlementArity-guided dIsentanglement network (PAIR), which can disentangle the features of multimodal queries from a semantic coherence perspective, thereby facilitating the identification of both complementary coherent and incoherent features. Furthermore, based on disentangled features, PAIR develops an asymmetric feature composition module, which is designed to enhance the retrieval performance of the model. Extensive experiments on three benchmark datasets demonstrate the superiority of PAIR. The code is available at https://***/***/.

关键词： Codes Accuracy Image retrieval Semantics Coherence Benchmark testing Signal processing Acoustics Speech processing Protection

来源：评论

学校读者我要写书评

暂无评论

FedFLD: Heterogeneous Federated Learning via Forget-Less Distillation

FedFLD: Heterogeneous Federated Learning via Forget-Less Dis...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaoyang Yi Jian Zhang Jing Chen Yuru Bao Lingkai Xing College of Cyber Science Nankai University China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China College of Computer Science Nankai University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated learning, as a distributed machine learning paradigm, enhances privacy protection but faces the challenge of heterogeneity. Data-free knowledge distillation (DFKD) methods attempt to overcome this challenge by using a generator to synthesize samples for fine-tuning a global model. However, these methods often suffer from significant shifts in output distribution, leading to catastrophic forgetting. To tackle these issues, we propose FedFLD, a novel federated forget-less distillation framework that mitigates catastrophic forgetting in DFKD while addressing the heterogeneity challenge. Specifically, FedFLD guides the generator’s training from three key aspects and constrains the output distribution with an elastic weight consolidation penalty term. By synthesizing diverse samples from different perspectives through additional generator updates, FedFLD facilitates effective knowledge distillation from local models to the global model. Additionally, the global model is further optimized via the heterogeneity fine-tuning process, mitigating the bias from heterogeneity and resulting in a more expressive and robust model.

关键词： Training Privacy Federated learning Signal processing Generators Acoustics Servers Speech processing Protection Faces

来源：评论

学校读者我要写书评

暂无评论

DSDIR: A Two-Stage Method for Addressing Noisy Long-Tailed Problems in Malicious Traffic Detection

DSDIR: A Two-Stage Method for Addressing Noisy Long-Tailed P...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Guoliang Li Ruiqi Zhang Zhe Sun Lingkai Xing Yu Zhang College of Cyber Science Nankai University China Tianjin Key Laboratory of Network and Data Security Technology China Key Laboratory of Data and Intelligent System Security Ministry of Education China College of Computer Science Nankai University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In recent years, deep learning based malicious traffic detection (MTD) systems have demonstrated remarkable success. However, their effectiveness tend to decrease because most malicious traffic datasets are suffered from noisy-labeled and long-tailed problems. While numerous approaches have been developed to address these two problems individually, they become inefficient when confronting the combined challenge of noisy long-tailed data, as they typically tackle only a single adverse factor at a time. This paper proposes a two-stage method called Distribution-aware sample Selection and Dynamic Instance-based Relabeling (DSDIR), which simultaneously addresses the impacts of noisy-labeled and long-tailed problems. In the first stage, a noise-independent clean sample selection method is designed to obtain a clean dataset, which converts negative effects of the long-tailed problem into positive ones. In the second stage, dynamic instance-based relabeling is designed to train a model and improve the dataset’s quality simultaneously. Eventually, DSDIR not only produces a balanced and noise-tolerant model but also obtains a clean dataset. Experimental results demonstrate that in the high noise condition of 60% and 80%, the accuracy rate of DSDIR is 5% higher than the state-of-the-art methods. Our code is available at https://***/nku-ligl/DSDIR.

关键词： Deep learning computer vision Heavily-tailed distribution Codes Accuracy Noise Speech recognition Acoustics Noise measurement Speech processing

来源：评论

学校读者我要写书评

暂无评论

MEDIAN: Adaptive Intermediate-grained Aggregation network for Composed Image Retrieval

MEDIAN: Adaptive Intermediate-grained Aggregation Network fo...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qinlei Huang Zhiwei Chen Zixu Li Chunxiao Wang Xuemeng Song Yupeng Hu Liqiang Nie School of Software Shandong University Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) School of Computer Science and Technology Shandong University School of Computer Science and Technology Harbin Institute of Technology (Shenzhen)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The Composed Image Retrieval (CIR) task aims to retrieve a target image that meets the requirements based on a given multimodal query (includes a reference image and modification text). Most existing works align multimodal semantics at both local and global granularity. However, they have failed to consider the mining of semantic correspondences at the intermediate-grained level, which has resulted in sub-optimal model performance. In this paper, we propose an adaptive interMEDiate-graIned Aggregation network (MEDIAN). Compared with the conventional CIR models, MEDIAN is capable of generating intermediate-grained feature aggregation supervised signals and constructing graph attention networks to extract intermediate-grained features. Concurrently, MEDIAN also devises cross-modal semantic correspondence aligning guided by the target image, which in turn enables accurate multi-grained feature composition. The superiority of MEDIAN is demonstrated by extensive experiments on three benchmark datasets. Our code is available at https://***/***/.

关键词： Adaptation models Adaptive systems Accuracy Codes Semantics Image retrieval Benchmark testing Signal processing Feature extraction Speech processing

来源：评论

学校读者我要写书评

暂无评论

UW-Adapter: Adapting Monocular Depth Estimation Model in Underwater Scenes

引用

IEEE Transactions on Multimedia 2025年

作者： Ye, Xinchen Chang, Yue Xu, Rui Li, Haojie DUT-RU International School of Information Science & Engineering Dalian University of Technology Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Liaoning China Shandong University of Science and Technology College of Computer Science and Engineering China

Estimating depth maps from monocular underwater images poses one of the most challenging problems in underwater applications. Due to the lack of large-scale paired underwater color-depth datasets for effective training, existing style transfer-based and self-supervision-based approaches can improve the performance of depth estimation to some extent, but they remain unsatisfactory. Leveraging the power of massive training datasets, foundation models designed for terrestrial monocular depth estimation have demonstrated superior performance across various scenes. These models provide rich prior knowledge of 3D perception, which can be valuable for underwater depth estimation. Upon this, we introduce tunable adapters (UW-Adapter) that tailor a pre-trained foundation model specifically for underwater depth estimation, customizing it to the unique characteristics of underwater imagery. Our approach involves freezing the parameters of the pre-trained model and updating only the adapters through self-supervision. To address the complex degradation of underwater images, we propose two adapters: the transmission adapter and the high-frequency adapter. These adapters incorporate depth clues and high-frequency information as prior knowledge, thereby enhancing the performance of pre-trained model in underwater depth estimation. Experimental results demonstrate that by integrating lightweight adapters into off-the-shelf depth estimation foundation models, our method achieves superior performance across multiple datasets. © 2025 IEEE.

关键词： Underwater photography

来源：评论

学校读者我要写书评

暂无评论

An Enhancing Stability Control Strategy of VSG-Based Power Source Under PWM Rectifier Load

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Gaoxiang Liu, Bowen Song, Wenhao Jining, Chen Liu, Xiao Guangxi University Guangxi Key Laboratory of Power System Optimization and Energy Technology School of Electrical Engineering Nanning530004 China Guangxi Zhuang Autonomous Region Information Center Guangxi Key Laboratory of Digital Infrastructure Nanning530200 China Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi Colleges and Universities Key Laboratory of Multimedia Communications and Information Processing School of Computer Electronics and Information Nanning530004 China

Under PWM rectifier load, the power source based on virtual synchronous generator (VSG) is prone to cause mid-frequency oscillation. Firstly, the system oscillation mechanism and characteristic of the VSG-based power source are analyzed based on impedance method. Due to the negative resistance and capacitive characteristic in the middle frequency range, the PWM rectifier load is prone to interact with the VSG-based power source, which can lead to impedance resonance. Secondly, to improve the stability of the VSG-based power source under the PWM rectifier load, a voltage differentiation feedforward control is proposed. In addition, since the mid-frequency impedance magnitude decrease obviously, the improved VSG-based power source is closer to the ideal voltage source, which can automatically suppress the middle harmonics induced by uncontrollable rectifier load. Finally, the proposed control and the corresponding theoretical analysis are verified by simulations and experiments. © 1975-2011 IEEE.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

DCCT-Net: A network Combined Dynamic CNN and Transformer for Image Compressive Sensing

DCCT-Net: A Network Combined Dynamic CNN and Transformer for...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Lijuan Xu Haixiao Mei Fenghua Tong Dawei Zhao Fuqiang Yu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent end-to-end image compressive sensing networks primarily use Convolutional Neural networks (CNNs) and Transformers, each with distinct limitations: CNNs struggle with global feature capture, while Transformers lack local feature extraction. We propose a novel network, DCCT-Net, which combines Dynamic CNN (DCNN) and Transformer. This integration leverages DCNN’s local feature strengths and the Transformer’s global representation capabilities, resulting in superior image reconstruction quality. To further enhance the network’s performance, we propose a Feature Dynamic Augment Module (FDAM), which dynamically extracts features based on the saliency of segmented image regions, thereby amplifying the CNN’s local feature expression. Additionally, we design a Weighted Fusion Module (WFM), which optimizes the combination of local and global features extracted by the DCNN and Transformer, respectively. Extensive experiments demonstrate that our proposed DCCT-Net significantly outperforms most existing state-of-the-art methods in the field.

关键词： Image segmentation Image coding Signal processing Transformers Feature extraction Sensors Convolutional neural networks Speech processing Compressed sensing Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multi-Relational Variational Contrastive Learning for Next POI Recommendation

Multi-Relational Variational Contrastive Learning for Next P...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Lin Chen Peipei Wang Xiaohui Han Lijuan Xu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Next point-of-interest (POI) recommendation aims to predict the next interested POI to the user based on their historical check-in data in location-based social services. Most existing studies have attempted to model user visiting behaviors via sequence-based and graph-based models, and have achieved impressive performance. However, there is still room to explore the implicit transition preferences and contextual multiple semantic relationships among various POIs. To this end, we propose a novel graph-based Multi-Relational Variational Contrastive Learning (MRVCL) method for next POI recommendation, which captures local similarity associations and global contextual dependencies among POIs. Specifically, an order-free local-relational adaptive weighting module is designed to alleviate the problem of insufficient utilization of multi-hop neighbor information caused by the limit of neighbor order of nodes. We then develop a contextaware global-relational encoding module to capture implicit semantic sequential relationships. Finally, generative variational-contrastive learning is employed to construct a continuous representation of the latent features and reinforce the quality of representation learning. Extensive experiments on two real-world datasets validate that our MRVCL outperforms existing state-of-the-art methods on various evaluation metrics. To facilitate future research, our code and data are open-sourced at https://***/LinCH-en/MRVCL.

关键词： Representation learning Measurement Correlation Semantics Neural networks Contrastive learning Signal processing Transformers Encoding Speech processing

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：