检索结果-内蒙古大学图书馆

International conference on Parallel and distributed Systems (ICPADS)

作者： Zhuang Han Jianfeng Guan Yanan Yao Su Yao School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9781665408790

network traffic classification has been highly concerned by academia and industry for decades. In recent years, deep learning has attracted many scholars to use it in network traffic classification due to its excellent performance in the fields of computer vision and natural language processing. However, the performance of the neural network depends on its structure in the same dataset. When looking for the neural network to classify network traffic, it is necessary to constantly adjust the structure of the neural network to achieve better results, which is very time-consuming and experience-dependent. To solve the above problem, this paper proposes an Adaptive Convolutional neural network Structure for network Traffic Classification (ACNNS-NTC) algorithm. The proposed algorithm first pre-processes the network traffic data used for training and testing, and then uses particle swarm optimization algorithm to optimize the network structure of the convolutional neural network, to generate convolutional neural network structure for network traffic classification, and verify the classification results. Experimental results show that the accuracies of the ACNNS-NTC algorithm on public datasets (ISCX-IDS2012, USTC-TFC2016, CIC-IDS2017) are above 99%. At the same time, the generated convolutional neural network has a more succinct structure and fewer model parameters compared with the existing methods.

关键词： Training Adaptive systems neural networks Telecommunication traffic Manuals Feature extraction Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

R-GAP: RECURSIVE GRADIENT ATTACK ON PRIVACY 9

R-GAP: RECURSIVE GRADIENT ATTACK ON PRIVACY

引用

9th International conference on Learning Representations, ICLR 2021

作者： Zhu, Junyi Blaschko, Matthew Dept. ESAT Center for Processing Speech and Images KU Leuven Belgium

Federated learning frameworks have been regarded as a promising approach to break the dilemma between demands on privacy and the promise of learning from large collections of distributed data. Many such frameworks only ask collaborators to share their local update of a common model, i.e. gradients, instead of exposing their raw data to other collaborators. However, recent optimization-based gradient attacks show that raw data can often be accurately recovered from gradients. It has been shown that minimizing the Euclidean distance between true gradients and those calculated from estimated data is often effective in fully recovering private data. However, there is a fundamental lack of theoretical understanding of how and when gradients can lead to unique recovery of original data. Our research fills this gap by providing a closed-form recursive procedure to recover data from gradients in deep neural networks. We name it Recursive Gradient Attack on Privacy (R-GAP). Experimental results demonstrate that R-GAP works as well as or even better than optimization-based approaches at a fraction of the computation under certain conditions. Additionally, we propose a Rank Analysis method, which can be used to estimate the risk of gradient attacks inherent in certain network architectures, regardless of whether an optimization-based or closed-form-recursive attack is used. Experimental results demonstrate the utility of the rank analysis towards improving the network's security. Source code is available for download from https://***/JunyiZhu-AI/R-GAP. © 2021 ICLR 2021 - 9th International conference on Learning Representations. All rights reserved.

关键词： network architecture

来源：评论

学校读者我要写书评

暂无评论

D-FGNAE: Decentralized Federated Graph Normalized AutoEncoder 19th

D-FGNAE: Decentralized Federated Graph Normalized AutoEncode...

引用

19th CCF conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Liang, Yuting Cai, Weixin Guo, Kun College of Computer and Data Science Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China

ISBN: (纸本)9789819623723

Graphs widely exist in real-world, and Graph neural networks (GNNs) have exhibited exceptional efficacy in graph learning in diverse fields. With the strengthening of data privacy protection worldwide in recent years, Federated graph neural networks (FedGNNs) have gained increasing attention in academia and industry owing to their ability to train the model in a collaborative manner while complying with the privacy protection regulations. However, in federated learning, the non-independent and identically distributed (non-IID) problem of local data possessed by multiple participants can significantly undermine model accuracy. We propose a new Decentralized Federated Graph Normalized AutoEncoder (D-FGNAE). First, the model is designed as a decentralized federated learning framework with dynamically assigned tripartite roles. This design eliminates the fixed server role found in traditional federated learning, enhances system fault tolerance, avoids single points of failure, and protects model privacy. Second, the splitting and correcting of calculation by layer in the model, along with the special design of the normalization layer, effectively tackle the non-IID problem in both the structural and attribute aspects. Experimental results on real-world networks demonstrate the effectiveness of D-FGNAE, which can achieve nearly the same accuracy as the centralized model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A robust multi-batch L-BFGS method for machine learning*

引用

OPTIMIZATION METHODS & SOFTWARE 2020年第1期35卷 191-219页

作者： Berahas, Albert S. Takac, Martin Lehigh Univ Dept Ind & Syst Engn Bethlehem PA 18015 USA

This paper describes an implementation of the L-BFGS method designed to deal with two adversarial situations. The first occurs in distributed computing environments where some of the computational nodes devoted to the evaluation of the function and gradient are unable to return results on time. A similar challenge occurs in a multi-batch approach in which the data points used to compute function and gradients are purposely changed at each iteration to accelerate the learning process. Difficulties arise because L-BFGS employs gradient differences to update the Hessian approximations, and when these gradients are computed using different data points the updating process can be unstable. This paper shows how to perform stable quasi-Newton updating in the multi-batch setting, studies the convergence properties for both convex and non-convex functions, and illustrates the behaviour of the algorithm in a distributed computing platform on binary classification logistic regression and neural network training problems that arise in machine learning.

关键词： L-BFGS multi-batch fault-tolerant sampling consistency overlap

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Improved Post-fire Debris Flow Likelihood Prediction

Machine Learning for Improved Post-fire Debris Flow Likeliho...

引用

IEEE International conference on Big Data

作者： Daniel Roten Jessica Block Daniel Crawl Jenny Lee Ilkay Altintas San Diego Supercomputer Center University of California San Diego La Jolla CA United States

ISBN: (纸本)9781665480468

Timely prediction of debris flow probabilities in areas impacted by wildfires is crucial to mitigate public exposure to this hazard during post-fire rainstorms. This paper presents a machine learning approach to amend an existing dataset of post-fire debris flow events with additional features reflecting existing vegetation type and geology, and train traditional and deep learning methods on a randomly selected subset of the data. The developed methods achieve AUC (area under the receiver operational characteristic curve) values of 0.93 (random forest) and 0.92 (neural network) on the test set, representing a significant improvement over a logistic regression model currently used (AUC 0.79). The paper also overviews a distributed, Kubernetesbased big data processing pipeline to efficiently retrieve features in areas impacted by new fires, and deploy the methods for real-time prediction of debris flow hazards.

关键词： Pipelines Vegetation Artificial neural networks Receivers Big Data Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection for Marine Meteorological Sensor network

Intrusion Detection for Marine Meteorological Sensor Network

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Xin Su Guifu Zhang Minxue Zhang Baoliu Ye Hongyan Xing College of IOT Engineering Hohai University Changzhou Jiangsu China Information Department Hohai University Nanjing Jiangsu China Collaborative Innovation Center for Meteorological Disaster Prediction and Evaluation Nanjing University of Information Science and Technology Nanjing China Jiangsu Key Laboratory of Meteorological Detection and Information Processing Nanjing University of Information Science and Technology Nanjing China

The rapid development of intelligent devices and wireless communication has greatly promoted the intelligence of the maritime Internet of Things (MIoT) in recent years, and the marine meteorological sensor network (MMSN) is an essential part of MIoT, providing accurate meteorological data for MIoT services. However, the frequent information interaction between the device and the external world also causes information leakage risks for MMSN. Intrusion detection technology based on deep learning is an effective defensive mechanism. Thus, we propose a lightweight one-dimensional convolutional neural network (LCNN) intrusion detection model to adapt to the MMSN environment characteristics and device heterogeneity. In addition, an improved supervised adversarial autoencoder (ISAAE) is proposed for synthesizing samples to address the problem that minority class attack samples are difficult to collect and detect. Finally, the simulation experimental results on the NSL-KDD dataset verify the effectiveness of the proposed method.

关键词： Training Wireless communication Adaptation models Convolution Computational modeling Simulation Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

distributed Information Integration in Convolutional neural networks 15

Distributed Information Integration in Convolutional Neural ...

引用

15th International Joint conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) / 15th International conference on Computer Vision Theory and Applications (VISAPP)

作者： Kumar, Dinesh Sharma, Dharmendra Univ Canberra Fac Sci & Technol 11 Kirinari St Canberra ACT 2617 Australia

ISBN: (纸本)9789897584022

A large body of physiological findings has suggested the vision system understands a scene in terms of its local features such as lines and curves. A highly notable computer algorithm developed that models such behaviour is the Convolutional neural network (CNN). Whilst recognising an object in various scales remains trivial for the human vision system, CNNs struggle to achieve the same behaviour. Recent physiological findings are suggesting two new paradigms. Firstly, the visual system uses both local and global features in its recognition function. Secondly, the brain uses a distributed processing architecture to learn information from multiple modalities. In this paper we combine these paradigms and propose a distributed information integration model called D-Net to improve scale-invariant classification of images. We use a CNN to extract local features and, inspired by Google's INCEPTION model, develop a trainable method using filter pyramids to extract global features called Filter Pyramid Convolutions (FPC). D-Net locally processes CNN and FPC features, fuses the outcomes and obtains a global estimate via the central processor. We test D-Net on classification of scaled images on benchmark datasets. Our results show D-Net's potential effectiveness towards classification of scaled images.

关键词： distributed Information Integration Central Processor Local Processor Convolutional neural network Filter Pyramid Scale-invariance

来源：评论

学校读者我要写书评

暂无评论

Light-weight Spiking Neuron processing Core For Large-scale 3D-NoC Based Spiking neural network processing Systems

Light-weight Spiking Neuron Processing Core For Large-scale ...

引用

IEEE International conference on Big Data and Smart Computing (BigComp)

作者： Ikechukwu, Ogbodo Mark Vu, The H. Dang, Khanh N. Ben Abdallah, Abderazek Univ Aizu Grad Sch Comp Sci & Engn Adapt Syst Lab Aizu Wakamatsu Fukushima 9658580 Japan Hung Yen Univ Technol & Educ Fac Infornat Technol Hung Yen Vietnam Vietnam Natl Univ Hanoi Univ Engn & Technol SISLAB Hanoi 123106 Vietnam

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160344

With the increasing demand for computing machines that more closely model the biological brain, the held of neuro-inspired computing has progressed to the exploration of Spiking neural networks (SNN), and to best the challenges of conventional Von Neumann architecture, several hardwarebased (neuromorphic) chips have been designed. A neuromorphic chip is based on spiking neurons that process input Information only when they receive spike signals Given a sparsely-distributed input spike train, the power consumption for such event-driven hardware would be reduced since large portions of the network that are not driven by incoming spikes can be set into a powergated mode. The challenges that need to be solved toward building in hardware such a spiking neuromorphk chip with a massive number of synapse include building small-sized spiking neuro-cores with low-power consumption, efhdent neurocoding scheme, and lightweight on-chip learning algorithm. In this paper, we present the hardware implementation and evaluation of a light-weight spiking neuron processing core (SNPC) for our 3DNoC SNN processor and the design of its on-chip learning block. The SNPC embeds 256 Leaky Integrate and Fire (LIF) neurons, and crossbar based synapses, covering a chip area of 0.12mm2. Its performance is evaluated ming rdNis-r damsel, achieving an inference accuracy of 97.55%.

关键词： Spiking neural network Neuromorphic 3D network on Chip Spiking Neuron processing Core

来源：评论

学校读者我要写书评

暂无评论

Distributing Deep Learning Inference on Edge Devices 20

Distributing Deep Learning Inference on Edge Devices

引用

16th International conference on Emerging networking Experiments and Technologies

作者： Gunarathne, Buddhi Prabhath, Chiranthana Ra, Vinura Pere Gunasekara, Kutila Univ Moratuwa Dept Comp Sci & Engn Katubedda Sri Lanka

ISBN: (纸本)9781450379489

Deep neural networks (DNNs) and Convolutional neural networks (CNNs) are widely used in IoT related applications. However, inferencing pre-trained large DNNs and CNNs consumes a significant amount of time, memory and computational resources. This makes it infeasible to use such DNNs/CNNs on resource constrained edge devices, In this research we are trying to implement a distributed inference schema for processing large DNNs and CNNs in such resource constrained edge devices. Our approach of solving this issue is based on partitioning DNNs/CNNs model and processing the inference tasks using two or more edge devices. Through this poster we introduce our novel approach of distributing the inference process among multiple edge devices while minimising the network overheads due to communication among devices. In addition to that, we present a task sharing mechanism among working devices and idle devices in the network and a way to convert pre-trained models to a separately executable model format.

关键词： distributed Computing Edge Computing distributed Inference Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Learning Dynamic Behavior Patterns for Fraud Detection

Learning Dynamic Behavior Patterns for Fraud Detection

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Zijun Huang Junhang Wu Lingfei Ren Ruimin Hu Dengshi Li National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Cyber Engineering Xidian University Xi'an China School of Artificial Intelligence Jianghan University Wuhan China

Telecom fraud detection is considered a needle in a haystack task due to the fact that fraudsters are usually hidden among a large number of normal users. In fact, a fraudster will usually act in a continuous manner over a period of time to achieve fraudulent purposes. At the same time, fraudsters are constantly looking for new fraudulent targets. Therefore, we consider a behavioral pattern-based fraudster identification system called HADyn-LSTM for telecommunication network fraud detection. Motivated by the breakthroughs in deep learning (DL), we make an effort to judge whether a user is a fraudster is based on the user's behavior sequence in the social network, which means that we study the difference between normal users and fraudsters through dynamic behavior patterns rather than static statistical attributes. Particularly, Based on sequential neural networks and attention mechanisms, we design an end-to-end system that learns and extracts the dynamic patterns of user behavior sequences. Furthermore, We tested our system on three datasets of different sizes. The test results show that the HADyn-LSTM system performs better than the static attribute-based method.

关键词： Social networking (online) neural networks Telephone sets Behavioral sciences Fraud Telecommunications Safety

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：