检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liang, Hanzhe Xie, Guoyang Hou, Chengbin Wang, Bingshu Gao, Can Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Audencia Financial Technology Institute Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Intelligent Manufacturing CATL Ningde China School of Computing and Artificial Intelligence Fuyao University of Science and Technology Fuzhou China School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we introduce a straightforward method named Internal Spatial Modality Perception (ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine (SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction module for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further aligning precise spatial structure. Extensive experiments validate the effectiveness of our proposed method, achieving object-level and pixel-level AUROC improvements of 4.2% and 13.1%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and is verified in both classification and segmentation tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

arXiv

引用

arXiv 2024年

作者： Wu, Xu Lai, Zhihui Jie, Zhou Gao, Can Hou, Xianxu Zhang, Ya-Nan Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well explored. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

ZETA: ZEro-Trust Attack Framework with Split Learning for Autonomous Vehicles in 6G Networks

ZETA: ZEro-Trust Attack Framework with Split Learning for Au...

引用

IEEE Conference on Wireless Communications and Networking

作者： Sunder Ali Khowaja Parus Khuwaja Kapal Dev Keshav Singh Lewis Nkenyereye Dan Kilper Faculty of Computing Digital and Data Technological University Dublin Ireland Institute of Business Administration University of Sindh Pakistan Department of Computer Science CONNECT Centre Munster Technological University Ireland Institute of Communications Engineering (ICE) National Sun Yat-sen University Taiwan Department of Computer and Information Security Sejong University South Korea CONNECT Centre School of Engineering Trinity College Dublin Ireland

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

In past, due to data and model security concerns, modern communication systems mainly focus on the use of edge computing devices for enabling immersive applications and services. Federated learning is one of the preferred solutions but it stresses the computation capability of the edge devices for immersive applications. Much research is now focusing on split learning as an alternative due to its ability of performing joint training with limited computing resources. However, split learning is also vulnerable to data reconstruction, feature space hijacking, and model inversion attacks, which are quite common concerning immersive applications such as Metaverse. In this regard, we propose a ZEro-Trust Attack (ZETA) framework for data reconstruction and model inversion attacks for autonomous vehicles opting for split learning strategies. We propose the joint training of client, server, and shadow models for both the reconstruction and main task to fool existing methods. Our experimental results demonstrate that the proposed method is capable of reconstructing client's data with an error of 0.0032. This study is proposed as a basis to design more sophisticated defense mechanisms for autonomous vehicles to protect user services in 5G/6G networks.

关键词： Training Performance evaluation Sensitivity analysis Computational modeling data models Zero Trust Servers

来源：评论

学校读者我要写书评

暂无评论

Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection

arXiv

引用

arXiv 2022年

作者： Liang, Siyuan Wu, Baoyuan Fan, Yanbo Wei, Xingxing Cao, Xiaochun Institute of Information Engineering Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China School of Data Science The Chinese University of Hong Kong Shenzhen China Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen China Tencent Shenzhen China Institute of Artificial Intelligence Hangzhou Innovation Institute Beihang University Beijing China

Object detection has been widely used in many safety-critical tasks, such as autonomous driving. However, its vulnerability to adversarial examples has not been sufficiently studied, especially under the practical scenario of black-box attacks, where the attacker can only access the query feedback of predicted bounding-boxes and top-1 scores returned by the attacked model. Compared with black-box attack to image classification, there are two main challenges in black-box attack to detection. Firstly, even if one bounding-box is successfully attacked, another suboptimal bounding-box may be detected near the attacked bounding-box. Secondly, there are multiple bounding-boxes, leading to very high attack cost. To address these challenges, we propose a Parallel Rectangle Flip Attack (PRFA) via random search. We explain the difference between our method with other attacks in Fig. 1. Specifically, we generate perturbations in each rectangle patch to avoid sub-optimal detection near the attacked region. Besides, utilizing the observation that adversarial perturbations mainly locate around objects' contours and critical points under white-box attacks, the search space of attacked rectangles is reduced to improve the attack efficiency. Moreover, we develop a parallel mechanism of attacking multiple rectangles simultaneously to further accelerate the attack process. Extensive experiments demonstrate that our method can effectively and efficiently attack various popular object detectors, including anchor-based and anchor-free, and generate transferable adversarial examples. Copyright © 2022, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Use of Large Language Model to Identify Top Research Priorities in Hematology

Evaluating the Use of Large Language Model to Identify Top R...

引用

2023 IEEE International Conference on E-Health Networking, Application and Services, Healthcom 2023

作者： Chen, Huiqin Huang, Fangwan Liu, Xuanyun Tan, Yinli Zhang, Dihua Li, Dongqi Borchert, Glen M. Tan, Ming Huang, Jingshan Sun Yatsen University Department of Pediatrics the Third Affiliated Hospital Guangzhou China College of Computer and Data Science Fuzhou University Fuzhou China Sun Yat-sen University Department of Nephrology the First Affiliated Hospital Guangzhou China University of California Irvine Department of Economics and School of Information and Computer Sciences Irvine United States College of Medicine University of South Alabama Department of Pharmacology Mobile United States Institute of Biochemistry and Molecular Biology Institute of Biomedical Sciences China Medical University Taichung Taiwan School of Computing College of Medicine University of South Alabama Mobile United States

ISBN: (纸本)9798350302301

The field of hematology is highly progressive and dynamic requiring researchers to commit significant amounts of time and effort towards staying abreast of the most crucial research areas. As such, in this work we assess the potential of ChatGPT for identifying research priorities within five key topics in hematology: acute lymphocytic leukemia, immunotherapy, targeted therapy, hematopoietic stem cell transplantation, and acute myeloid leukemia. After ChatGPT was employed to generate specific research questions in these areas, a panel of seven experienced hematologists independently reviewed and rated resultant research questions based on four parameters: relevance, originality, clarity, and specificity on a scale of 1 to 5, with 5 denoting the highest score. Excitingly, the mean and median grades of the four parameters were all above 4, indicating that the hematologists strongly agreed that the problems generated by ChatGPT were generally highly specific, clear, relevant, and original. As such, although further work will clearly be required, we suggest our current study indicates that Large Language Models (LLMs), such as ChatGPT, may very well represent valuable new tools for more efficiently identifying and prioritizing impactful research questions in the field of hematology. © 2023 IEEE.

关键词： Stem cells

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

arXiv

引用

arXiv 2024年

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-Sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Implementing Multi-factor Authentication in Cloud Services for Enhanced Security

Implementing Multi-factor Authentication in Cloud Services f...

引用

Recent Advances in science and Engineering Technology (ICRASET), International Conference on

作者： K. Sashi Rekha V.M. Sivagami R. Usharani T Amutha S. Pushparani Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Information Technology Sri Venkateswara College of Engineering Chennai Tamil Nadu India Department of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India Department of Artificial Intelligence & Data Science CARE College of Engineering Trichy Tamil Nadu India Department of Computer Science and Engineering Meenakshi College of Engineering Chennai Tamil Nadu India

ISBN: (数字)9798350388602

ISBN: (纸本)9798350388619

The cloud services which are now the most common data transmission and endanger organizations’ confidential information, it’s more and more visible that security of any data should be a main priority for companies. MFA, which consists of adopting multi factor approach to authentication and thereby provides multiple types of verification thus ensures effective security, is leveraged to ensure resource access. This paper proposes a full-fledged way of implementing MFA for cloud services in order to strengthen the security given and manage the constatoing risks. The proposed methodology consists of main stages like requirements determining, technology reviewing, risks assessment, technology design, integration with cloud services, users training, pilot deployment and testing, implementation and configuration, monitoring and maintenance as well as constant improvement. Through a systemic approach, the organizations can be equipped with the capability to personalize the MFA solutions according to their security goals, to bring the cloud environments on board, as well as to ensure that the organizations comply with the security standards as set by various governing bodies. This research adds a grain of salt to the development of cloud security good practices through offering a disciplined approach to MFA implementation, which allows partners to harden their cloud assets and protect against growing cyber threats.

关键词： Training Cloud computing Multi-factor authentication Standards organizations Companies Regulation Maintenance Security Protection Monitoring

来源：评论

学校读者我要写书评

暂无评论

Simulate the Machine Learning Algorithm to Organize the CRAHN Network System

Simulate the Machine Learning Algorithm to Organize the CRAH...

引用

Advancement in Electronics & Communication Engineering (AECE), International Conference on

作者： P Prabakaran L. Chandra Sekhar Reddy LVD Ravikumar Manish Kumar Verma Department Of Computer Applications School of computing sciences Vels Institute of Science Technology and Advanced Studies Chennai India Department of CSE(Data Science) CMR College of Engineering & Technology Medchal Hyderabad India Department of Information Technology Shri Vishnu Engineering College For Women Bhimavaram India Department of Psychology Lovely Professional University Phagwara India

Using available channels in a wireless spectrum, cognitive radio (CR) may automatically adjust transmission settings to optimize radio operational behaviour. To function properly, a CR ad hoc network (CRAHN) has to be dynamically capable construct autonomous and decentralized networks without negatively impacting licensed main user (PU) systems. For this reason, an effective spectrum necessitates a system structure based on artificial intelligence. This research provides a model for network planning, learning, and dynamic configuration that is based on a distributed autonomous CRAHN network system that uses reinforcement learning. The proposed optimization techniques for spectrum sensing, ad hoc network design, and context-aware signal categorization are all derived from the system model and are based on machine learning. The cognitive and detection engines may be used to examine the spectrum utilization and neighbour network status in the immediate area. To adapt to the ever-changing nature of the wireless environment, the suggested policy engine may generate network operating policies, identify policy conflicts, and infer the best course of action. Together with the erudition engine, whereby apply the recommended machine-learning methods, the decision engine arrives at the best possible settings for the CRAHN. In addition, guarantee peaceful cohabitation with surrounding systems to have excellent signal context recognition ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Innovative Deep Learning Techniques for Solving Complex Computer Vision Challenges and Enhancing Pattern Recognition Accuracy

Innovative Deep Learning Techniques for Solving Complex Comp...

引用

Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC), International Conference on

作者： T. Jayachitra S. Sathya Ramesh P S Jothikumar R Gouri M. S Mohammed Waheeduddin Hussain Department of Electrical Electronics and Communication Engineering Sharda University Greater Noida India Department of Artificial Intelligence and Data Science GRT Institute of Engineering and Technology Tiruttani India Department of Smart Computing Vellore Institute of Technology Vellore India Department of Computer Science and Engineering Shadan College of Engineering and Technology Hyderabad India Department of Computer Science and Engineering Baselios Mathews - II College of Engineering Sasthamcotta Kollam India Department of Information Technology Shadan College of Engineering and Technology Peerancheru Hyderabad India

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

The proposed work provides an in-depth analysis of DL techniques to enhance pattern recognition accuracy in difficult computer vision applications. This background explains the present status of the problems in the area and motivates the development of a complex framework that blends innovative neural network topologies, state-of-the-art optimization approaches, and inventive data augmentation strategies. Among the methods are CNNs enhanced with residual blocks and attention mechanisms, which are implemented using the TensorFlow deep learning framework. The results demonstrate significant improvements over baseline models on a number of measures. Using the CIFAR-10 dataset, the proposed system achieves an impressive 92.5% accuracy and 92.1% F1-score for classification tasks. With an IoU of 78.2% and a mAP of 81.4% in object identification tasks, the system shows its robustness in accurately localizing and recognizing things within photos. These findings have practical ramifications for industries needing accurate visual identification, such autonomous driving and medical imaging, in addition to advancing theoretical knowledge. The efficacy of the architecture highlights its potential to serve as a benchmark for next deep learning studies and applications.

关键词： Deep learning Computer vision Visualization Accuracy Network topology Neural networks data augmentation Topology Pattern recognition Object recognition

来源：评论

学校读者我要写书评

暂无评论

A Joint Gradient and Loss Based Clustered Federated Learning Design

arXiv

引用

arXiv 2023年

作者： Lin, Licheng Chen, Mingzhe Yang, Zhaohui Wu, Yusen Liu, Yuchen Department of Electrical and Computer Engineering University of Miami Coral GablesFL33146 United States Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Department of Computer Science North Carolina State University RaleighNC27695 United States

In this paper, a novel clustered FL framework that enables distributed edge devices with non-IID data to independently form several clusters in a distributed manner and implement FL training within each cluster is proposed. In particular, our designed clustered FL algorithm must overcome two challenges associated with FL training. First, the server has limited FL training information (i.e., the parameter server can only obtain the FL model information of each device) and limited computational power for finding the differences among a large amount of devices. Second, each device does not have the data information of other devices for device clustering and can only use global FL model parameters received from the server and its data information to determine its cluster identity, which will increase the difficulty of device clustering. To overcome these two challenges, we propose a joint gradient and loss based distributed clustering method in which each device determines its cluster identity considering the gradient similarity and training loss. The proposed clustering method not only considers how a local FL model of one device contributes to each cluster but also the direction of gradient descent thus improving clustering speed. By delegating clustering decisions to edge devices, each device can fully leverage its private data information to determine its own cluster identity, thereby reducing clustering overhead and improving overall clustering performance. Simulation results demonstrate that our proposed clustered FL algorithm can reduce clustering iterations by up to 99% compared to the existing baseline. Copyright © 2023, The Authors. All rights reserved.

关键词： Gradient methods

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：