检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Yanmeng Ji, Wenkai Zhou, Jian Xiao, Fu Chang, Tsung-Hui School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China

Federated learning (FL) has emerged as a promising distributed learning paradigm for training deep neural networks (DNNs) at the wireless edge, but its performance can be severely hindered by unreliable wireless transmission and inherent data heterogeneity among clients. Existing solutions primarily address these challenges by incorporating wireless resource optimization strategies, often focusing on uplink resource allocation across clients under the assumption of homogeneous client-server network standards. However, these approaches overlooked the fact that mobile clients may connect to the server via diverse network standards (e.g., 4G, 5G, Wi-Fi) with customized configurations, limiting the flexibility of server-side modifications and restricting applicability in real-world commercial networks. This paper presents a novel theoretical analysis about how transmission failures in unreliable networks distort the effective label distributions of local samples, causing deviations from the global data distribution and introducing convergence bias in FL. Our analysis reveals that a carefully designed client selection strategy can mitigate biases induced by network unreliability and data heterogeneity. Motivated by this insight, we propose FedCote, a client selection approach that optimizes client selection probabilities without relying on wireless resource scheduling. Experimental results demonstrate the robustness of FedCote in DNN-based classification tasks under unreliable networks with frequent transmission failures. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Hard-Label Black-Box Attacks on 3D Point Clouds

arXiv

引用

arXiv 2024年

作者： Liu, Daizong Tao, Yunbo Zhou, Pan Hu, Wei Wangxuan Institute of Computer Technology Peking University No. 128 Zhongguancun North Street Beijing China The Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

With the maturity of depth sensors in various 3D safety-critical applications, 3D point cloud models have been shown to be vulnerable to adversarial attacks. Almost all existing 3D attackers simply follow the white-box or black-box setting to iteratively update coordinate perturbations based on back-propagated or estimated gradients. However, these methods are hard to deploy in real-world scenarios (no model details are provided) as they severely rely on parameters or output logits of victim models. To this end, we propose point cloud attacks from a more practical setting, i.e., hard-label black-box attack, in which attackers can only access the prediction label of 3D input. We introduce a novel 3D attack method based on a new spectrum-aware decision boundary algorithm to generate high-quality adversarial samples. In particular, we first construct a class-aware model decision boundary, by developing a learnable spectrum-fusion strategy to adaptively fuse point clouds of different classes in the spectral domain, aiming to craft their intermediate samples without distorting the original geometry. Then, we devise an iterative coordinate-spectrum optimization method with curvature-aware boundary search to move the intermediate sample along the decision boundary for generating adversarial point clouds with trivial perturbations. Experiments demonstrate that our attack competitively outperforms existing white/black-box attackers in terms of attack performance and adversary quality. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Lightweight Transformer Network and Self-supervised Task for Kinship Verification 8

Lightweight Transformer Network and Self-supervised Task for...

引用

8th IEEE International Conference on computer and Communications, ICCC 2022

作者： Zhu, Xiaoke Li, Yunwei Li, Danyang Dong, Lingyun Chen, Xiaopan School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University China

ISBN: (纸本)9781665450515

Kinship verification is one of the interesting and critical problems in computer vision research, with significant progress in the past decades. Meanwhile, Vision Transformer (VIT) has recently achieved impressive success in many domains, including object detection, image recognition, and semantic segmentation, among others. Most of the previous work on kinship verification are based on convolutional or recurrent neural networks. Compared with the local processing of images like convolutions, transformers can effectively understand and process images globally. However, due to overuse, there are many Transformer layers of fully connected layers, and VIT speed is still an issue. Therefore, in this paper, inspired by the recent success of Transformer models in vision tasks, we propose a Transformer-based kinship verification for training and optimizing kinship verification models. We first train the basic vision transformer (VIT-B) with 12 transformer layers, then we reduce the transformer layers to 6 layers, namely VIT-S (Small Vit) and 4 layers, namely VIT-T (Tiny Vit), to make a tradeoff between optimization accuracy and efficiency. As the first attempt to apply Transformer to the kinship verification task, it provides a feasible strategy for kinship research topics and verifies the effectiveness of the method in terms of the accuracy of the experimental results. © 2022 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Segmentation and Quantization Algorithm for Infarct Size Measurement of Rat Heart Sections 8

Semi-supervised Segmentation and Quantization Algorithm for ...

引用

8th IEEE International Conference on computer and Communications, ICCC 2022

作者： Zhu, Xiaoke Cai, Yulong Chen, Xiaopan Hu, Qi Dong, Lingyun Yuan, Caihong School of Computer and Information Engineering Henan University Kaifeng China Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University China

ISBN: (纸本)9781665450515

Segmentation of rat heart section images and infarct area quantization are essential components of infarct size measurement in processing data from animal experiments on ischemic heart disease. Previously, the task of measuring the infarct size of rat heart sections was performed manually by experienced researchers, which was very costly and time-consuming. In this paper, we propose a two-stage semi-supervised approach to solve the task of ischemic heart infarct size calculation in images of rat section images. The approach uses a semi-supervised semantic segmentation model and a semi-automated quantization algorithm to separate the differently stained regions of rat heart sections. We demonstrate the results of the approach on a rat heart section dataset, and experiments on this dataset emphasize the effectiveness of our approach compared to other methods. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

How graph neural networks learn: lessons from training dynamics 24

How graph neural networks learn: lessons from training dynam...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Chenxiao Yang Qitian Wu David Wipf Ruoyu Sun Junchi Yan School of Artificial Intelligence & Department of Computer Science and Engineering & MoE Lab of AI Shanghai Jiao Tong University Amazon Web Services School of Data Science The Chinese University of Hong Kong Shenzhen and Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions they can represent, but whether GNNs will learn desired functions during the optimization process remains less clear. To fill this gap, we study their training dynamics in function space. In particular, we find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function, as can be quantified by a phenomenon which we call kernel-graph alignment. We provide theoretical explanations for the emergence of this phenomenon in the overparameterized regime and empirically validate it on real-world GNNs. This finding offers new interpretable insights into when and why the learned GNN functions generalize, highlighting their limitations in heterophilic graphs. Practically, we propose a parameter-free algorithm that directly uses a sparse matrix (i.e. graph adjacency) to update the learned function. We demonstrate that this embarrassingly simple approach can be as effective as GNNs while being orders-of-magnitude faster.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ENSIOT: A Stacking Ensemble Learning Approach for IoT Device Identification

ENSIOT: A Stacking Ensemble Learning Approach for IoT Device...

引用

International Workshop on Quality of Service

作者： Kangli Niu Shenghao Liu Lingzhi Yi Xianjun Deng Suning Chen Laurence T. Yang Minmin Cheng Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Safety Engineering Zhongnan University of Economics and Law

ISBN: (数字)9798350350128

ISBN: (纸本)9798350350135

In order to resist network attacks on IoT devices, identifying IoT devices is the first step for ensuring device security. The traditional passive method identifies IoT devices by mining the potential relationship between traffic characteristics and devices. However, the form of selected traffic features are too singular without considering device behavioral characteristics and the classifier used is too specific with simple structure in these methods. This paper proposes a stacking ensemble learning approach for IoT device identification, ENSIOT, which fully considering the behavioral characteristics of devices and integrating the advantages of various machine learning methods to achieve efficient identification of IoT devices. Firstly, in the process of traffic processing, our method selects features from activity cycles, port numbers, signalling patterns, and cipher suites. Then, in model integration, many machine learning methods are used as base models to learn features selected, and output preliminary recognition results. Finally, the meta model learns the relationship between label and the recognition results of each base model and outputs the final device identification result. This stacking structure stacks the base models and the meta model to make a classifier with strong identification and generalization ability. Incremental learning is used to improve identification accuracy when traffic pattern changing. Comparative experiments are conducted on two datasets of UNSW and TMA-2021. The experimental results verify the effectiveness of ENSIOT, which achieve the accuracy of over 98% on two dataset and bring a noticeable improvement in terms of both accuracy and macro F1 score.

关键词： Ciphers Accuracy Incremental learning Stacking Resists Traffic control Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Reversible data hiding scheme for encrypted JPEG bitstreams using adaptive RZL rotation

引用

Frontiers of Information Technology & Electronic engineering 2024年第10期25卷 1353-1369页

作者： Yongning GUO Guodong SU Zhiqiang YAO Wang ZHOU School of Big Data and Artificial Intlligence Fujian Polytechnic Normal UniversityFuzhou 350300China College of Mathematics and Informatics Fujian Normal UniversityFuzhou 350117China Engineering Research Center for ICH Digitalization and Multi-Source Information Fusion(Fujian Polytechnic Normal University) FujianProvinceUniversityFuzhou350300China School of Computer and Sofiware Engineering Xihua UniversityChengdu 610039China

Joint Photographic Experts Group(JPEG)format is extensively used for images in many practical applications due to its excellent compression ratio and satisfactory image *** compelling concerns about the invasion of privacy,this paper proposes an effective reversible data hiding scheme for encrypted JPEG bitstreams,to provide security and privacy for both secret messages and valuable ***,a format-compatibility and file size preserving encryption algorithm is applied to encipher the plaintext JPEG image into a noise-like ***,we present an effective reversible data hiding scheme in encrypted JPEG bitstreams using adaptive RZL rotation,where the secret messages are concealed with the sequence of RZL *** the authorized user receives the marked encrypted JPEG bitstreams,the error-free extraction of secret messages and the lossless recovery of the original plaintext JPEG image can be accomplished *** experiments are conducted to show that,compared to some state-of-the-art schemes,the proposed scheme has a superior performance in terms of embedding capacity,while keeping file size preservation and format compatibility.

关键词： Joint Photographic Experts Group(JPEG) Reversible data hiding Embedding capacity File size preservation Format compatibility

来源：评论

学校读者我要写书评

暂无评论

Task Separation and Knowledge Sharing for Class Incremental Learning

Task Separation and Knowledge Sharing for Class Incremental ...

引用

Intelligent Computing and Human-computer Interaction (ICHCI), International Conference on

作者： Jiali Zhang Xiaoyan Qiao Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center School of Computer Science and Technology Shandong Technology and Business University Yantai Shandong China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center School of Mathematics and Information Science Shandong Technology and Business University Yantai Shandong China

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory.

关键词： Knowledge engineering Human computer interaction Degradation Incremental learning Computational modeling Memory management Information sharing Network architecture Feature extraction Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification

arXiv

引用

arXiv 2025年

作者： Ma, Yi Wang, Shuai Liu, Tianchi Li, Haizhou The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The Institute for Infocomm Research A*STAR 138632 Singapore Shenzhen Research Institute of Big data School of Data Science The Chinese University of Hong Kong Shenzhen518172 China

In speaker verification, we use computational method to verify if an utterance matches the identity of an enrolled speaker. This task is similar to the manual task of forensic voice comparison, where linguistic analysis is combined with auditory measurements to compare and evaluate voice samples. Despite much success, we have yet to develop a speaker verification system that offers explainable results comparable to those from manual forensic voice comparison. A novel approach, Explainable Phonetic Trait-Oriented (ExPO) network, is proposed in this paper to introduce the speaker’s phonetic trait which describes the speaker’s characteristics at the phonetic level, resembling what forensic comparison does. ExPO not only generates utterance-level speaker embeddings but also allows for fine-grained analysis and visualization of phonetic traits, offering an explainable speaker verification process. Furthermore, we investigate phonetic traits from within-speaker and between-speaker variation perspectives to determine which trait is most effective for speaker verification, marking an important step towards explainable speaker verification. Our code is available at https://***/mmmmayi/ExPO. Copyright © 2025, The Authors. All rights reserved.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers

Robin: A Novel Method to Produce Robust Interpreters for Dee...

引用

IEEE International Conference on Automated Software engineering (ASE)

作者： Zhen Li Ruqian Zhang Deqing Zou Ning Wang Yating Li Shouhuai Xu Chen Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security Department of Computer Science University of Colorado Colorado Springs USA Center for Research in Computer Vision University of Central Florida USA School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier; the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA.

关键词：

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：