检索结果-内蒙古大学图书馆

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Schrick, Noah L. Hawrylak, Peter J. U.S. Army Corps of Engineers Engineer Research and Development Center Information Technology Laboratory VicksburgMS United States Tandy School of Computer Science College of Engineering and Computer Science The University of Tulsa TulsaOK United States

ISBN: (纸本)9798331504847

The generation of large-scale graphs encounters unique challenges compared to the exploration of the same large-scale graphs. Attack graphs and compliance graphs can be useful applications of large-scale graphs in order for organizations to understand and analyze their cybersecurity or regulatory standings, but their generation can often be prohibitive. This work introduces a data-parallel distributed approach of large-scale graph generation with the specific application of attack and compliance graphs. This approach aims to distribute the exploratory states of a graph across compute nodes in order to compile groups of subgraphs that will compose the full graph. This work utilizes Message-Passing Interface as the standard for passing messages across nodes in the distributed generator program. Additional experimentation, results, and discussions are also provided regarding the viability of using a Distributed Hash Table. This work presents a first step, naïve approach to subgraphing, and discusses potentially viable alternatives for increased performance. © 2025 IEEE.

关键词： Belief propagation

来源：评论

学校读者我要写书评

暂无评论

Heterogeneity Modeling with Flexibility-based Graph Neural Networks 22

Heterogeneity Modeling with Flexibility-based Graph Neural N...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Qin, Jisheng Tao, Tao Liu, Zijie Chen, Haibo Zhao, Shenghui Chuzhou University School of Computer and Information Engineering Anhui Chuzhou China Anhui University of Technology School of Computer Science and Technology Anhui Ma'anshan China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Anhui University of Technology China

ISBN: (纸本)9798331509712

Graph Neural Networks (GNNs) have demonstrated robust performance in various graph-based machine learning tasks, especially in homophilous graphs, where edges tend to connect nodes with the same label. However, achieving consistent performance on heterophilous graphs remains challenging. Several works have extended GNN architectures to address the distinct characteristics of heterogeneous graphs. However, these methods often need to enhance the flexibility of handling feature combinations for the central node and its neighbors. In this paper, we introduce a novel approach to modeling heterogeneity with Flexibility-based Graph Convolutional Networks (FGCN). FGCN consists of two primary components: first, it independently encodes the central node and its neighbors, fusing them to obtain an output representation. Second, it aggregates nodes with the same label from a feature and neighbor perspective, imposing constraints on the transformation during graph structure propagation. This approach enhances the flexibility of combining the central node and neighbor representations. We conducted extensive experiments on eight real-world datasets, demonstrating that FGCN outperforms state-of-the-art (SOTA) baseline models. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Cognitive Memory-Augmented Network for Visual Anomaly Detection

引用

IEEE/CAA Journal of Automatica Sinica 2021年第7期8卷 1296-1307页

作者： Tian Wang Xing Xu Fumin Shen Yang Yang the Center for Future Multimedia and School of Computer Science and Engineering University of Electronic Science and Technology of China(UESTC)Chengdu 611731China the Center for Future Multimedia and School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731 the Institute of Electronic and Information Engineering of UESTC in Guangdong Dongguan 523808China

With the rapid development of automated visual analysis,visual analysis systems have become a popular research topic in the field of computer vision and automated *** analysis systems can assist humans to detect anomalous events(e.g.,fighting,walking alone on the grass,etc).In general,the existing methods for visual anomaly detection are usually based on an autoencoder architecture,i.e.,reconstructing the current frame or predicting the future ***,the reconstruction error is adopted as the evaluation metric to identify whether an input is abnormal or *** flaws of the existing methods are that abnormal samples can also be reconstructed *** this paper,inspired by the human memory ability,we propose a novel deep neural network(DNN)based model termed cognitive memory-augmented network(CMAN)for the visual anomaly detection *** proposed CMAN model assumes that the visual analysis system imitates humans to remember normal samples and then distinguishes abnormal events from the collected ***,in the proposed CMAN model,we introduce a memory module that is able to simulate the memory capacity of humans and a density estimation network that can learn the data *** reconstruction errors and the novelty scores are used to distinguish abnormal events from *** addition,we develop a two-step scheme to train the proposed model so that the proposed memory module and the density estimation network can cooperate to improve *** experiments evaluated on various popular benchmarks show the superiority and effectiveness of the proposed CMAN model for visual anomaly detection comparing with the state-of-the-arts *** implementation code of our CMAN method can be accessed at https://***/CMANcode/CMAN_pytorch.

关键词： Cognitive computing density estimation memory visual analysis systems visual anomaly detection.

来源：评论

学校读者我要写书评

暂无评论

The Client-Level GAN-Based Data Reconstruction Attack and Defense in Clustered Federated Learning 18th

The Client-Level GAN-Based Data Reconstruction Attack and D...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Wu, Han Shi, Lei Ye, Junyu Fan, Yuqi Lv, Zengwei School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei230009 China

ISBN: (纸本)9783031714634

Clustered Federated Learning (CFL) is an innovative architecture that effectively tackles the challenge of data heterogeneity in Federated Learning (FL). However, such a setup also introduces vulnerabilities that can be exploited by attackers to execute more severe attacks. This paper compares the efficacy of data reconstruction attacks utilizing Generative Adversarial Nets (GANs) in FL and CFL, respectively. It also proposes a general client-level data reconstruction attack scheme whose key is in that the attackers can eavesdrop the victim’s partial uploaded parameters. Experimental results demonstrate that the sample data generated in this kind of attack within the scenario of CFL exhibit a higher degree of similarity with the targeted data compared to FL. And it is observed that the attacks involving eavesdropping in CFL perform more effectively with a client-level attack accuracy. In addition, we design a lightweight and adaptive local differential privacy (LDP) mechanism to defend against this kind of attack. In this method, under the premise that the differential privacy budget decreases as the number of training round adds, each client dynamically adjusts the probability of adding differential privacy noise and the size of DP’s parameters according to the training accuracy and the resemblance to the reconstructed data generated by attackers. Our defense method can effectively alleviate the loss of training accuracy for each client caused by the accumulation of the differential privacy budget while ensuring the defense effect, and it also reduces clients’ computational burden. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Classification of Adversarial Attacks Using Ensemble Clustering Approach

引用

computers, Materials & Continua 2023年第2期74卷 2479-2498页

作者： Pongsakorn Tatongjai Tossapon Boongoen Natthakan Iam-On Nitin Naik Longzhi Yang Center of Excellence in AI&Emerging Technologies School of ITMae Fah Luang UniversityChiang RaiThailand Department of Computer Science Aberystwyth UniversityAberystwythUnited Kingdom School of Informatics and Digital Engineering Aston UniversityBirminghamUnited Kingdom Department of Computer and Information Sciences Northumbria UniversityNewcastleUnited Kingdom

As more business transactions and information services have been implemented via communication networks,both personal and organization assets encounter a higher risk of *** safeguard these,a perimeter defence likeNIDS(network-based intrusion detection system)can be effective for known *** has been a great deal of attention within the joint community of security and data science to improve machine-learning based NIDS such that it becomes more accurate for adversarial attacks,where obfuscation techniques are applied to disguise patterns of intrusive *** current research focuses on non-payload connections at the TCP(transmission control protocol)stack level that is applicable to different network *** contrary to the wrapper method introduced with the benchmark dataset,three new filter models are proposed to transform the feature space without knowledge of class *** ECT(ensemble clustering based transformation)techniques,i.e.,ECT-Subspace,ECT-Noise and ECT-Combined,are developed using the concept of ensemble clustering and three different ensemble generation strategies,i.e.,random feature subspace,feature noise injection and their *** on the empirical study with published dataset and four classification algorithms,new models usually outperform that original wrapper and other filter alternatives found in the *** is similarly summarized from the first experiment with basic classification of legitimate and direct attacks,and the second that focuses on recognizing obfuscated *** addition,analysis of algorithmic parameters,i.e.,ensemble size and level of noise,is provided as a guideline for a practical use.

关键词： Intrusion detection adversarial attack machine learning feature transformation ensemble clustering

来源：评论

学校读者我要写书评

暂无评论

Prediction of Passenger Flow During Peak Hours Based on Deep Learning 7th

Prediction of Passenger Flow During Peak Hours Based on Deep...

引用

7th International Conference on Information science, Communication and Computing, ISCC 2023

作者： Li, Yajing Cheng, Jieren Kou, Yuqing Xia, Dongwan Sheng, Victor S. School of Computer Science and Technology Hainan University Haikou570228 China Hainan Blockchain Technology Engineering Research Center Haikou570228 China Department of Computer Science Texas Tech University LubbockTX79409 United States

ISBN: (纸本)9789819971602

In many deep learning tasks, feature extraction and fusion in multivariate time series is an indispensable part of passenger flow prediction. Because there is also a certain correlation between passenger flow time series, it is very meaningful to successfully capture the time characteristics of the series and the dependencies between each series. Therefore, this study combined Residual Network (ResNet) and Attention Gated Recurrent Unit (Attention GRU) to build a ResGRU model for predicting subway passenger flow data during peak hours. This study has improved ResNet and attention GRU, then designed the ResGRU model architecture. Among them, the subway network topology is constructed by graphs, ResNet is used to capture the hidden spatial features between data, attention GRU captures the deep temporal features between data. This study not only considered passenger flow data, but also added subway network topology data, even weather and air pollution index data. Finally, three time solts of 10, 15 and 30 min were used to forecast the peak passenger flow on the public dataset. The ResGRU model was compared with the single model, the combined model and an ablation experiment. The experimental results demonstrate the high robustness and superiority of the model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Person Re-Identification Based on Instance Segmentation and Pose Estimation 6

Person Re-Identification Based on Instance Segmentation and ...

引用

6th IEEE International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Zhou, Yao Qin, Yusong Wang, Song Huang, Zengxi Zhang, Dazhi Xihua University School of Computer Science and Software Engineering Chengdu China Xihua University School of Computer and Software Engineering and the Sichuan Xihua Jiaotong Forensics Center Chengdu China Sichuan Police College Criminal Science and Technology Department Luzhou China

ISBN: (纸本)9798350325485

Person Re-Identification (ReID) is a crucial task in computer vision that aims to match persons captured from non-overlapping camera views. In this paper, to alleviate the impacts of background and occlusion, we propose to use instance segmentation and pose estimation methods to create masks for global feature extraction. Furthermore, we divide the pedestrian images into three regions according to pedestrian keypoints, trying to eliminate the alignment errors. This part-based matching strategy also helps to address the occlusion issue. Overall, we construct a deep learning network with three branches, including two global branches and a part-based branch. The two global branches extract global features using segmentation-based mask and the mask derived from pedestrian keypoint heatmaps, respectively. In the end, a weighted fusion strategy is used to combine the global scores and part-based scores for final classification. This network enables us to acquire robust global feature of pedestrians by excluding background and occlusion, and simultaneously address the alignment errors to some extent. Experimental results on these three widely used datasets demonstrate the effectiveness of our method: Specifically, it achieves 64.5% rank-1 accuracy and 54.3% mAP on Occluded-Duke, and 94.4% and 87.1% rank-1 accuracies on Market-1501 and DukeMTMC-reID, respectively. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

FourierFilter irregular attention U-Net with multi-receptive field fusion for cell nucleus segmentation

引用

Journal of Intelligent and Fuzzy Systems 2024年第5-6期47卷 471-485页

作者： Zhang, Xingpeng Pan, Yunfeng Wang, Qiuli Yang, Mo Xiao, Bin School of Computer Science Southwest Petroleum University Chengdu China Engineering Research Center for Intelligent Oil Gas Exploration and Development of Sichuan Province Chengdu China Department of Radiology The First Affiliated Hospital Army Medical University Chongqing China

Cell nucleus segmentation plays a significant role in computer-Aided systems for cancer diagnosis. However, the nuclear images are characterized by different sizes, overlap, adhesion, and similarities between nuclei and other structures, making this task challenging. Aiming to adjust and enhance the feature learning ability of the network, this paper proposes a FourierFilter Irregular Attention U-Net (FFIA-UNet), which contains FourierFilter Irregular Attention (FFIA) and multi-receptive filed fusion (MRF) module. FFIA module seeks to learn deeper characteristics by taking advantage of frequency information and deformable convolution. MRF module improve the learning capacity of fuzzy edges and irregular forms via multiple dilated convolution. Experiments on three datasets show that the proposed FFIA-UNet achieves state-of-the-art. Dice-Score and mIoU reached 0.929 and 0.885 respectively on DSB2018. Furthermore, numerous ablation experiments have demonstrated the module's efficacy. © 2024 - IOS Press. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Method for Abnormal Detection and Poisoned Data Recovery in Clustered Federated Learning 18th

A Method for Abnormal Detection and Poisoned Data Recovery...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Chen, Yingying Shi, Lei Xu, Hao Ye, Junyu Xu, Juan School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei230009 China

ISBN: (纸本)9783031714665

Clustered Federated Learning (CFL), as a type of Federated Learning (FL) paradigm, divides the clients into multiple clusters through the clustering process and trains them within the clusters, thus improving the overall model training accuracy. But the clustering process is also the weak link, which can lead to the failure of the whole model training if it is interfered or destroyed by the attacker. In this paper, we study the attack methods and defense strategies for attackers to implement data poisoning by tampering with client data, resulting in overall clustering failure. Our defense approach is designed to identify anomalous clients and recover their poisoned data. In order to resist the malicious behavior of attackers, we propose a dual-threshold pixel difference and watermark authentication defense method for detecting the presence of anomalous clients. The method can accurately identify the abnormal fluctuations in the data and effectively screen out the abnormal clients. Meanwhile, we propose a self-embedding watermarking defense algorithm based on shuffling idea for recovering poisoned data. Among them, our self-embedding watermarking algorithm not only accurately locates and recovers the tampered region of the image, but also improves the watermark security to prevent attackers from cracking it easily. Simulation results show that our proposed algorithm can accurately identify the abnormal client and recover the data. Even if the client’s data is massively tampered with, we can recover the tampered data images with high quality and ensure that the CFL clustering is not corrupted. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Revisiting Kernel Attention with Correlated Gaussian Process Representation 40

Revisiting Kernel Attention with Correlated Gaussian Process...

引用

40th Conference on Uncertainty in Artificial Intelligence, UAI 2024

作者： Bui, Long Minh Huu, Tho Tran Dinh, Duy Nguyen, Tan Minh Hoang, Trong Nghia FPT Software AI Center Department of Mathematics National University of Singapore Singapore School of Electrical Engineering and Computer Science Washington State University United States

Transformers have increasingly become the de facto method to model sequential data with state-of-the-art performance. Due to its widespread use, being able to estimate and calibrate its modeling uncertainty is important to understand and design robust transformer models. To achieve this, previous works have used Gaussian processes (GPs) to perform uncertainty calibration for the attention units of transformers and attained notable successes. However, such approaches have to confine the transformers to the space of symmetric attention to ensure the necessary symmetric requirement of their GP’s kernel specification, which reduces the representation capacity of the model. To mitigate this restriction, we propose the Correlated Gaussian Process Transformer (CGPT), a new class of transformers whose self-attention units are modeled as cross-covariance between two correlated GPs (CGPs). This allows asymmetries in attention and can enhance the representation capacity of GP-based transformers. We also derive a sparse approximation for CGP to make it scale better. Our empirical studies show that both CGP-based and sparse CGP-based transformers achieve better performance than state-of-the-art GP-based transformers on a variety of benchmark tasks. © 2024 Proceedings of Machine Learning Research. All rights reserved.

关键词： Distribution transformers

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：