检索结果-内蒙古大学图书馆

22nd IEEE International Symposium on Parallel and distributed processing with Applications, ISPA 2024

作者： Zhang, Jin Sa, RuLa An, Qi Gao, QiaoMei Pang, Xiliang Yu, Meiju Inner Mongolia University School of Computer Science Hohhot China

ISBN: (纸本)9798331509712

Social media, with its immediacy and convenience, has become an important channel for people to exchange information. However, this freedom of information dissemination also provides a breeding ground for the spread of disinformation. Because the image will inevitably leave traces in the process of tampering and compression. Therefore, this paper proposes a convolutional neural network model SE-CNN, which, combined with the SE attention module, designs two inputs, on the one hand accepting the original image and on the other hand converting the image into error Level Analysis (ELA) format. The open source dataset CASIA V1.0 was selected for testing in this article. The experimental results show that the accuracy of this model on this dataset is 99.22%, which has stronger generalization ability than the traditional CNN model. © 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

TurboMGNN: Improving Concurrent GNN Training Tasks on GPU With Fine-Grained Kernel Fusion

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2023年第6期34卷 1968-1981页

作者： Wu, Wenchao Shi, Xuanhua He, Ligang Jin, Hai Huazhong Univ Sci & Technol Natl Engn Res Ctr Big Data Technol & Syst Sch Comp Sci & Technol Serv Comp TechnolCluster & Grid Comp Lab Wuhan 430074 Peoples R China Univ Warwick Dept Comp Sci Coventry CV4 7AL England

Graph neural networks (GNN) have evolved as powerful models for graph representation learning. Many works have been proposed to support GNN training efficiently on GPU. However, these works only focus on a single GNN training task such as operator optimization, task scheduling, and programming model. Concurrent GNN training, which is needed in the applications such as neural network structure search, has not been explored yet. This work aims to improve the training efficiency of the concurrent GNN training tasks on GPU by developing fine-grained methods to fuse the kernels from different tasks. Specifically, we propose a fine-grained Sparse Matrix Multiplication (SpMM) based kernel fusion method to eliminate redundant accesses to graph data. In order to increase the fusion opportunity and reduce the synchronization cost, we further propose a novel technique to enable the fusion of the kernels in forward and backward propagation. Finally, in order to reduce the resource contention caused by the increased number of concurrent, heterogeneous GNN training tasks, we propose an adaptive strategy to group the tasks and match their operators according to resource contention. We have conducted extensive experiments, including kernel- and model-level benchmarks. The results show that the proposed methods can achieve up to 2.6X performance speedup.

关键词： Task analysis Training Graphics processing units Kernel Graph neural networks Computational modeling Fuses GNN training concurrent multi-tasks GPU kernel fusion

来源：评论

学校读者我要写书评

暂无评论

Ethereum Phishing Detection Using Hyperbolic neural networks and Temporal Information 22

Ethereum Phishing Detection Using Hyperbolic Neural Networks...

引用

22nd IEEE International Symposium on Parallel and distributed processing with Applications, ISPA 2024

作者： Xu, Rong Zhang, Jun Zhu, Xiaoyue Song, Zhaoxiong Yu, Zhi Inner Mongolia University College of Computer Science Hohhot China Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798331509712

In recent years, the frequent occurrence of phishing scams on Ethereum has posed serious threats to transaction security and the financial safety of users. This paper proposes an Ethereum phishing scam detection method based on Hyperbolic neural networks (HGNNs) and temporal information. The method maps the Ethereum transaction network to hyperbolic space for structural feature extraction, effectively capturing hierarchical structures and complex relationships within the graph, thereby improving the accuracy of phishing scam detection. The model includes a structural feature extraction module and a temporal feature extraction module. It uses HGNN and self-attention mechanism to extract the structural features of the transaction graph, and uses a multi-head attention mechanism to capture the dynamic evolution pattern of the graph. Experimental validation on real Ethereum datasets demonstrates that the proposed model outperforms benchmark models, showcasing its effectiveness. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

neural network-based distributed denial of service (DDoS) attack detection in smart home networks

Neural network-based distributed denial of service (DDoS) at...

引用

6th Smart Cities Symposium (SCS 2022)

作者： I. Ahamed F. Ahamad V. Palade A. Ahamed Centre for Future Transport and Cities Coventry University Coventry UK Centre for Computational Science and Mathematical Modelling Coventry University Coventry UK School of Engineering Canterbury Christ Church University Canterbury UK

Due to various limitations, such as limited power supply, the lack of storage capability and processing power, Internet of Things-based smart home networks have become vulnerable to various cyber-security attacks including distributed Denial of Service (DDoS) attacks. These attacks are a malicious attempt to exhaust and overwhelm the target system resources, which has significant impact on the operation of smart home net- works. This paper proposes a novel, efficient and lightweight DDoS attack detection scheme in smart home networks, which employs artificial neural networks (ANN) to classify smart home networks traffic into DDoS attacks or normal traffic. The proposed solution is evaluated on four datasets, namely, IoT-23, DS2OS, NUSW-NB15GT and CICDDOS2019. Experiments were conducted on two types of ANN models, i.e., Multilayered Perceptron (MLP) and Long- Short-Term Memory (LSTM), which achieved 99.78% and 99.98% accuracy, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Point Cloud Video Recognition Acceleration Framework Based on Tempo-Spatial Information

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2023年第12期34卷 3224-3237页

作者： Song, Zhuoran Liu, Wanzhen Yang, Tao Liu, Fangxin Jing, Naifeng Liang, Xiaoyao Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China Huawei Technol Co Ltd Shenzhen 518129 Peoples R China

In point cloud video recognition (PVR) tasks, deep neural networks (DNNs) have been widely adopted to enhance accuracy. However, real-time processing is hindered due to the increasing volume of points and frames that require processes. Point clouds represent 3D-shaped discrete objects using a multitude of points. Consequently, these points often exhibit an uneven distribution in the view space, resulting in strong spatial similarity within each point cloud frame. Taking advantage of this observation, this article introduces PRADA, a Point Cloud Recognition Acceleration algorithm via Dynamic Approximation. PRADA approximates and eliminates the similar local pairs' computations and recovers their results by copying dissimilar local pairs' features for speedup with negligible accuracy loss. Furthermore, considering the slow changes in point cloud frames that lead to the high temporal similarity among points across multiple frames, we design PointV, a Point Cloud Video Recognition Acceleration algorithm, to minimize unnecessary computations of similar points in the temporal domain. Moreover, we propose the PRADA and PointV architectures to accelerate the PRADA and PointV algorithms. These two architectures can be integrated to gain higher performance improvement. Our experiments on a wide variety of datasets show that PRADA averagely achieves about 7 x speedup over 1080TI GPU. In addition, the experimental results show that the PointV architecture and the integrated architecture can respectively achieve 11.7x and 13.9x performance improvement with acceptable accuracy compared to the 1080TI GPU.

关键词： Point cloud compression Task analysis Heuristic algorithms Streaming media Computer architecture Approximation algorithms Artificial neural networks Point cloud video recognition task deep neural network acceleration tempo-spatial information accelerator

来源：评论

学校读者我要写书评

暂无评论

Detecting Smart Contract Vulnerabilities based on Fusing Semantic and Syntax Structure Information 22

Detecting Smart Contract Vulnerabilities based on Fusing Sem...

引用

22nd IEEE International Symposium on Parallel and distributed processing with Applications, ISPA 2024

作者： Gu, Xiguo Duan, Xinhong Ren, Senlin Zhang, Jiale Cui, Zhanqi Beijing Information Science and Technology University School of Computer Science Beijing China

ISBN: (纸本)9798331509712

Due to the widespread application and economic value of smart contracts, they have become targets for attackers, leading to significant economic losses from vulnerabilities. Therefore, it is crucial to detect potential vulnerabilities in smart contracts before they are deployed. However, existing machine learning approaches often overlook the type information of nodes and edges, while those based on heterogeneous graphs only utilize the semantic information of smart contracts, neglecting the syntax structure information. This oversight compromises the performance in detecting vulnerabilities. To address these issues, we propose a novel smart contract vulnerability detection approach named HG-Detector(Heterogeneous Graph Detector), which stands for Heterogeneous Graph Detector. This approach integrates semantic and syntax structure information by employing a heterogeneous graph neural network to analyze the source code of smart contracts. It extracts both semantic and syntax structure information and then uses a classifier to detect potential vulnerabilities. Experimental results on a dataset comprising 1269 smart contracts show that, compared to MANDO, HG-Detector has achieved an average increase of 10.06% in Precision, an average increase of 1.61% in Recall, an average increase of 2.29% in the F1, and an average increase of 4.78% in Accuracy across seven types of vulnerabilities © 2024 IEEE.

关键词： Heterogeneous abstract syntax tree Heterogeneous control flow graph Heterogeneous function call graph Heterogeneous Graph neural network Smart contract

来源：评论

学校读者我要写书评

暂无评论

PROACTIVE DDoS ATTACKS DETECTION USING DEEP LEARNING TECHNIQUES

PROACTIVE DDoS ATTACKS DETECTION USING DEEP LEARNING TECHNIQ...

引用

International Conference on Green Energy, Computing and Intelligent Technology 2024, GEn-CITy 2024

作者： Kumar, Gurugubelli Ravi Krishna, Bhukya Ramesh, Choppa Gandhi Institute of Engineering and Technology University Odisha Gunupur India Aditya Institute of Technology and management Andhrapradesh Tekkali India

ISBN: (纸本)9781837242689

In this study, present a comprehensive analysis of detecting distributed Denial of Service (DDoS) attacks using advanced deep learning models, including a Deep neural network (DNN), Convolutional neural network (CNN), and Long Short-Term Memory (LSTM) network. Leveraging the CICDDoS2019 dataset, we evaluate the performance of these models across several metrics, such as accuracy, precision, recall, F1-score, log-loss, and ROC-AUC, to determine their efficacy in distinguishing DDoS attack traffic from normal traffic. The DNN model achieves an impressive accuracy of 98.31% and near-perfect precision and recall values, highlighting its robustness in capturing the characteristics of DDoS attacks. The CNN model, while effective, shows a slightly lower accuracy of 97.27%, indicating its limitations in processing complex sequential dependencies. The LSTM model, designed to learn from temporal patterns, demonstrates a solid performance with an accuracy of 96.78% and high recall, making it suitable for sequence-based detection scenarios. Furthermore, our analysis of log-loss values reveals that the LSTM model achieves the lowest value, indicating strong model confidence, while the ROC-AUC values emphasize the exceptional discriminative capabilities of all models, with the DNN model performing the best. These results underline the potential of deep learning techniques in enhancing DDoS attack detection, with each model offering distinct strengths depending on the data characteristics and detection requirements. © The Institution of Engineering & Technology 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Equipping Federated Graph neural networks with Structure -aware Group Fairness 23

Equipping Federated Graph Neural Networks with Structure -aw...

引用

23rd IEEE International Conference on Data Mining (IEEE ICDM)

作者： Cui, Nan Wang, Xiuling Wang, Wendy Hui Chen, Violet Ning, Yue Stevens Inst Technol 1 Castle Point Terrace Hoboken NJ 07030 USA

ISBN: (纸本)9798350307887

Graph neural networks (GNNs) arc used for graph data processing across various domains. Centralized training of GNNs often faces challenges due to privacy and regulatory issues, making federated learning (FL) a preferred solution in a distributed paradigm. However, GNNs may inherit biases from training data, causing these biases to propagate to the global model in distributed scenarios. To address this issue, we introduce F(2)GNN, a Fair Federated Graph neural network, to enhance group fairness. Recognizing that bias originates from both data and algorithms, F(2)GNN aims to mitigate both types of bias under federated settings. We offer theoretical insights into the relationship between data bias and statistical fairness metrics in GNNs. Building on our theoretical analysis, F(2)GNN features a fairness -aware local model update scheme and a fairness -weighted global model update scheme, considering both data bias and local model fairness during aggregation. Empirical evaluations show F(2)GNN outperforms SOTA baselines in fairness and accuracy.

关键词： Graph neural networks Federated Learning Group Fairness

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Over Coupled Graphs

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2023年第4期34卷 1159-1172页

作者： Lei, Runze Wang, Pinghui Zhao, Junzhou Lan, Lin Tao, Jing Deng, Chao Feng, Junlan Wang, Xidian Guan, Xiaohong XianJiaotong Univ MOE Key Lab Intelligent Networks & Network Secur Xian 710049 Shaanxi Peoples R China China Mobile Res Inst Beijing 100875 Peoples R China China Mobile Grp Design Inst Beijing 100080 Peoples R China Tsinghua Univ Ctr Intelligent & Networked Syst Tsinghua Natl Lab Informat Sci & Technol Beijing 100084 Peoples R China

Graphs are widely used to represent the relations among entities. When one owns the complete data, an entire graph can be easily built, therefore performing analysis on the graph is straightforward. However, in many scenarios, it is impractical to centralize the data due to data privacy concerns. An organization or party only keeps a part of the whole graph data, i.e., graph data is isolated from different parties. Recently, Federated Learning (FL) has been proposed to solve the data isolation issue, mainly for Euclidean data. It is still a challenge to apply FL on graph data because graphs contain topological information which is notorious for its non-IID nature and is hard to partition. In this work, we propose a novel FL framework for graph data, FedCog, to efficiently handle coupled graphs that are a kind of distributed graph data, but widely exist in a variety of real-world applications such as mobile carriers' communication networks and banks' transaction networks. We theoretically prove the correctness and security of FedCog. Experimental results demonstrate that our method FedCog significantly outperforms traditional FL methods on graphs. Remarkably, our FedCog improves the accuracy of node classification tasks by up to 14.7%.

关键词： distributed graph processing federated learning graph neural networks privacy preservation

来源：评论

学校读者我要写书评

暂无评论

Exploiting Processor Heterogeneity to Improve Throughput and Reduce Latency for Deep neural network Inference 36

Exploiting Processor Heterogeneity to Improve Throughput and...

引用

36th IEEE International Symposium on Computer Architecture and High-Performance Computing, SBAC-PAD 2024

作者： Beaumont, Olivier David, Jean-Francois Eyraud-Dubois, Lionel Thibault, Samuel Inria Center of the University of Bordeaux Bordeaux France University of Bordeaux Bordeaux France

ISBN: (纸本)9798350356168

The growing popularity of Deep neural networks (DNNs) in a variety of domains, including computer vision, natural language processing, and predictive analytics, has led to an increase in the demand for computing resources. Graphics processing Units (GPUs) are widely used for training and inference of DNNs. However, this exclusive use can quickly lead to saturation of GPU resources while CPU resources remain underutilized. This paper proposes a performance evaluation of a solution that exploits processor heterogeneity by combining the computational power of GPUs and CPUs. A solution is proposed for distributing the computational load across the different processors to optimize their utilization and achieve better performance. A solution for partitioning a DNN model with different computational resources is proposed. This solution transfers part of the load from the GPUs to the CPUs when necessary to reduce latency and increase throughput. The partitioning of DNN models is performed using METIS to balance the computational load to be distributed among the different resources while minimizing communication. The experimental results show that latency and throughput are improved for a number of DNN models. Potential applications include real-time processing systems such as autonomous vehicles, drones, and video surveillance systems where minimizing latency and maximizing throughput are critical. © 2024 IEEE.

关键词： Graphics processing unit

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：