检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yao, Jianrong Pang, Lihui Su, Yang Zhang, Zhi Yang, Wei Fu, Anmin Gao, Yansong School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Electrical Engineering University of South China Hengyang China Security engineering laboratory Sungkyunkwan University Korea Republic of The School of Computer Science The University of Adelaide Adelaide Australia Data61 CSIRO Sydney Australia

Physical Unclonable Function (PUF) is a hardware security primitive with a desirable feature of low cost. Considering the space of challenge-response pairs (CRPs), there are two PUF categories: weak PUF and strong PUF. Compared to a weak PUF, a strong PUF has a wider range of applications. However, it is challenging to design a reliable and secure lightweight strong PUF. To address this challenge, PUF recomposition built upon multiple simple PUF instances has received a lot of attention in research, such as the most popular XOR-APUF, the recent MPUF in IEEE TC 2017 [1], XOR-FF-APUF in IEEE TIFS 2020 [2] and IPUF in TCHES 2020 [3]. When a combination of MAX and MIN (equal to AND and OR) bitwise operations are used in PUF recomposition [4]-[6], its resilience against model attacks was expected to be improved markedly, because one bitwise operation might be vulnerable to one type of modeling attack and combining them can yield improved resilience. To our knowledge, there is no explicit evaluation of this recomposition, thus, this study is the first to evaluate the uniformity and reliability of the OR-AND-XOR-PUF (OAX-PUF)-(x, y, z)-OAX-PUF. Compared to the most used l-XOR-PUF, the (x, y, z)-OAX-PUF shows better reliability given l = x + y + z without degrading the uniformity (i.e., retain to be 50%). As APUF is a compact PUF instance for constructing lightweight strong PUF candidates, e.g., XOR-APUF, MUXPUF and IPUF, we further examine the modeling resilience of the (x, y, z)-OAX-APUF using four powerful attacks, i.e., logistic regression (LR), reliability assisted CMA-ES, multilayer perceptron (MLP), and the most recent hybrid LR-reliability. Compared to the XOR-APUF, the OAX-APUF successfully defeats the CMA-ES attack. It often shows improved modeling resilience against LR and hybrid LR-reliability attacks while always increasing the attacking time costs of these two attacks. However, OAX-APUF exhibits lower modeling resilience against the MLP attack unless the x, y,

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

MCoCo: Multi-level Consistency Collaborative Multi-view Clustering

arXiv

引用

arXiv 2023年

作者： Zhou, Yiyang Zheng, Qinghai Yan, Wenbiao Wang, Yifei Shi, Pengcheng Zhu, Jihua School of Software Engineering Xi’an Jiaotong University Xi’an710049 China College of Computer and Data Science Fuzhou University Fuzhou350108 China

Multi-view clustering can explore consistent information from different views to guide clustering. Most existing works focus on pursuing shallow consistency in the feature space and integrating the information of multiple views into a unified representation for clustering. These methods did not fully consider and explore the consistency in the semantic space. To address this issue, we proposed a novel Multi-level Consistency Collaborative learning framework (MCoCo) for multi-view clustering. Specifically, MCoCo jointly learns cluster assignments of multiple views in feature space and aligns semantic labels of different views in semantic space by contrastive learning. Further, we designed a multi-level consistency collaboration strategy, which utilizes the consistent information of semantic space as a self-supervised signal to collaborate with the cluster assignments in feature space. Thus, different levels of spaces collaborate with each other while achieving their own consistency goals, which makes MCoCo fully mine the consistent information of different views without fusion. Compared with state-of-the-art methods, extensive experiments demonstrate the effectiveness and superiority of our method. Our code is released on https://***/YiyangZhou/MCoCo. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Entropy-based Probabilistic Forwarding Strategy in Named data Networking

An Entropy-based Probabilistic Forwarding Strategy in Named ...

引用

IEEE International Conference on Communications

作者： Kai Lei Jiawei Wang Jie Yuan Institute of Big Data Technologies Shenzhen Key Lab for Cloud Computing Technology & Applications School of Electronics and Computer Engineering (SECE) Peking University

ISBN: (纸本)9781467364300

The forwarding strategy is the key to the resiliency and efficiency of Named data Networking (NDN), which is a new and fundamental research area. For forwarding strategy, dynamically selecting an optimal interface from multiple alternative interfaces to forward an Interest packet is indeed a multiple attribute decision making (MADM) problem. In this paper, an entropy-based probabilistic forwarding (EPF) strategy is proposed to make a stochastic interface selection based on the combination of interfaces' dynamic availabilities and static routing information, which achieves better load balance in comparison with deterministic interface selection. By objectively assigning weights to attributes and considering multiple real-time network condition metrics, EPF can obtain the availabilities of interfaces more accurately and comprehensively. Since additional network metrics can be easily added and integrated into interfaces' assessment model, EPF provides good extensibility. In addition, we innovatively define two parameters (γ, δ) which can be used to trade off the effect factors between static routing information and dynamic running status of interfaces to customize EPF strategy for different network and application scenarios. Experiments show that EPF can realize preferable load balance and achieve higher throughput compared to the representative BestRoute forwarding strategy.

关键词： Entropy Throughput Routing Probabilistic logic Load modeling Packet loss

来源：评论

学校读者我要写书评

暂无评论

UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes

UpCycling: Semi-supervised 3D Object Detection without Shari...

引用

International Conference on computer Vision (ICCV)

作者： Sunwook Hwang Youngseok Kim Seongwon Kim Saewoong Bahk Hyung-Sin Kim Department of Electrical and Computer Engineering Seoul National University SK Telecom Seoul Korea Graduate School of Data Science Seoul National University

Semi-supervised Learning (SSL) has received increasing attention in autonomous driving to reduce the enormous burden of 3D annotation. In this paper, we propose UpCycling, a novel SSL framework for 3D object detection with zero additional raw-level point cloud: learning from unlabeled de-identified intermediate features (i.e., "smashed" data) to preserve privacy. Since these intermediate features are naturally produced by the inference pipeline, no additional computation is required on autonomous vehicles. However, generating effective consistency loss for unlabeled feature-level scene turns out to be a critical challenge. The latest SSL frameworks for 3D object detection that enforce consistency regularization between different augmentations of an unlabeled raw-point scene become detrimental when applied to intermediate features. To solve the problem, we introduce a novel combination of hybrid pseudo labels and feature-level Ground Truth sampling (F-GT), which safely augments unlabeled multi-type 3D scene features and provides high-quality supervision. We implement UpCycling on two representative 3D object detection models: SECOND-IoU and PV-RCNN. Experiments on widely-used datasets (Waymo, KITTI, and Lyft) verify that UpCycling outperforms other augmentation methods applied at the feature level. In addition, while preserving privacy, UpCycling performs better or comparably to the state-of-the-art methods that utilize raw-level unlabeled data in both domain adaptation and partial-label scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-scale north-to-south genetic admixture profile in Shaanxi Han Chinese revealed by genome-wide demographic history reconstruction

引用

植物分类学报 2022年第4期60卷 955-972页

作者： Guang-Lin He Meng-Ge Wang Ying-Xiang Li Xing Zou Hui-Yuan Yeh Ren-Kuan Tang Xiao-Min Yang Zheng Wang Jian-Xin Guo Ting Luo Jing Zhao Jin Sun Rong Hu Lan-Hai Wei Gang Chen Yi-Ping Hou Chuan-Chao Wang Department of Anthropology and Ethnology Institute of AnthropologyNational Institute for Data Science in Health and MedicineState Key Laboratory of Marine Environmental ScienceState Key Laboratory of Cellular Stress Biologyand School of Life SciencesXiamen UniversityXiamen 361005China Institute of Forensic Medicine West China School of Basic Science and Forensic MedicineSichuan UniversityChengdu 610065China Institute of Forensic Medicine West China School of Basic Science and Forensic MedicineSichuan UniversityChengdu 610065China Department of Anthropology and Ethnology Institute of AnthropologyNational Institute for Data Science in Health and MedicineState Key Laboratory of Marine Environmental ScienceState Key Laboratory of Cellular Stress Biologyand School of Life SciencesXiamen UniversityXiamen 361005China School of Humanities Nanyang Technological UniversityNanyang 639798Singapore Department of Forensic Medicine College of Basic MedicineChongqing Medical UniversityChongqing 400331China Hunan Key Laboratory of Bioinformatics School of Computer Science and EngineeringCentral South UniversityChangsha 410075China

The Han Chinese are the world's largest ethnic group residing across *** province in northern China was a pastoral-agricultural interlacing region sensitive to climate change since Neolithic times,which makes it a vital place for studying population ***,genetic studies of Shaanxi Han are underrepresented due to the lack of high-density sampling and genome-wide ***,we genotyped 700 000 single nucleotide polymorphisms(SNPs)in 200 Han individuals from nine populations in Shaanxi and compared with available modem and ancient Eurasian *** revealed a north-south genetic cline in Han Chinese with Shaanxi Han locating at the northern side of the *** detected the western Eurasian-related admixture in Shaanxi populations,especially in Guanzhong and Shanbei Han Chinese in proportions of 2％-4.6％.Shaanxi Han were suggested to derive a large part of ancestry(39％-69％)from a lineage that also contributed largely to ancient and present-day Tibetans(85％)as well as southern Han,supporting the common northern China origin of modem Sino-Tibetan-speaking populations and southwestward expansion of millet farmers from the middle-upper Yellow River Basin to the Tibetan Plateau and to southern *** rest of the ancestry of Shaanxi Han was from a lineage closely related to ancient and present-day Austronesian and Tai-Kadai speaking populations in southern China and Southeast *** also observed a genetic substructure in Shaanxi Han in terms of north-south-related ancestry corresponding well to the *** mitochondrial DNA and paternal Y-chromosome lineages further demonstrated the aforementioned admixture pattern of Han Chinese in Shaanxi province.

关键词： ancestral makeup genetic relationship haplogroup Northern Han population substructure western Eurasian admixture

来源：评论

学校读者我要写书评

暂无评论

Ghost-in-Wave: How Speaker-Irrelative Features Interfere DeepFake Voice Detectors

Ghost-in-Wave: How Speaker-Irrelative Features Interfere Dee...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xuan Hai Xin Liu Zhaorun Chen Yuan Tan Song Li Weina Niu Gang Liu Rui Zhou Qingguo Zhou School of Information Science and Engineering Lanzhou University Lanzhou China Elmore Family School of Electrical and Computer Engineering Purdue University IN USA The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Recent speech synthesis technology can generate high-quality speech indistinguishable from human speech, thus introducing various security and privacy risks. Numerous recent studies have focused on fake voice detection to address these risks, with many claiming to achieve ideal performance. However, is this really the case? A recent research work introduced Speaker-Irrelative-Features (SiFs), unrelated to the information in speech files but capable of influencing fake detectors. This means that existing detectors may rely on SiFs to a certain extent to distinguish real and fake speech. In this paper, we introduce an evaluation framework to evaluate the influence of SiFs in existing fake voice detectors in depth. We evaluate three SiFs which include background noise, the mute parts before and after voice, and the sampling rate on ASVspoof2019 and FoR. Our results confirm the substantial influence of SiFs on fake voice detection performance, and we delve into the analysis of the underlying mechanisms.

关键词： Privacy Deepfakes Detectors Feature extraction Background noise Speech synthesis Security

来源：评论

学校读者我要写书评

暂无评论

Synergizing Vision and Language in Remote Sensing: A Multimodal Approach for Enhanced Disaster Classification in Emergency Response Systems

Synergizing Vision and Language in Remote Sensing: A Multimo...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Shubham Gupta Nandini Saini Suman Kundu Chiranjoy Chattopadhyay Debasis Das Computer Science & Engineering Indian Institute of Technology Jodhpur Rajasthan India School of Computing and Data Sciences FLAME University Pune Maharashtra India

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

As remote sensing capabilities continue to advance, there is a growing interest in leveraging computer vision and natural language processing for enhanced interpretation of remote sensing scenes. This paper explores the integration of textual information with images to augment traditional disaster classification methods. Our approach utilizes a predefined vision-language model to generate descriptive captions for images, fostering a more nuanced understanding of the remote sensing data. Next, we seamlessly integrate the generated textual information with image data through multimodal training, employing a multimodal deep learning method for disaster classification. The system categorizes input data into predefined disaster categories, presenting a comprehensive and accurate approach to emergency response system development. Experimental evaluations conducted on the AIDER dataset (Aerial Image database for Emergency Response applications) showcase the efficacy of our approach, demonstrating improved accuracy compare to unimodal approach and reliability in disaster classification. This research contributes to the advancement of intelligent emergency response systems by harnessing the synergy between vision and language in the context of remote sensing.

关键词： Training Accuracy Social networking (online) Image databases Disasters Emergency services Real-time systems

来源：评论

学校读者我要写书评

暂无评论

RIBCAGEIMP: A DEEP LEARNING FRAMEWORK FOR 3D RIBCAGE IMPLANT GENERATION

arXiv

引用

arXiv 2024年

作者： Chaubey, Gyanendra Farooq, Aiman Singh, Azad Mishra, Deepak School of AI and Data Science IIT RJ Jodhpur342030 India Department of Computer Science and Engineering IIT RJ Jodhpur342030 India

The recovery of damaged or resected ribcage structures requires precise, custom-designed implants to restore the integrity and functionality of the thoracic cavity. Traditional implant design methods rely mainly on manual processes, making them time-consuming and susceptible to variability. In this work, we explore the feasibility of automated ribcage implant generation using deep learning. We present a framework based on 3D U-Net architecture that processes CT scans to generate patient-specific implant designs. To the best of our knowledge, this is the first investigation into automated thoracic implant generation using deep learning approaches. Our preliminary results, while moderate, highlight both the potential and the significant challenges in this complex domain. These findings establish a foundation for future research in automated ribcage reconstruction and identify key technical challenges that need to be addressed for practical implementation. Copyright © 2024, The Authors. All rights reserved.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Text-Video Completion Networks With Motion Compensation And Attention Aggregation

Text-Video Completion Networks With Motion Compensation And ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jianan Wang Zhiliang Wu Hanyu Xuan Yan Yan School of Computer Science and Engineering Nanjing University of Science and Technology China CCAI Zhejiang University China School of Big Data and Statistics Anhui University China Department of Computer Science Illinois Institute of Technology USA

The purpose of video inpainting is to fill a specified area with reasonable content. However, in the case of multiple targets and complex textures, current methods struggle to distinguish between feature information of the targets, leading to confusing or fuzzy inpainting results. In this paper, we design a new text-video completion network based on a motion compensation and temporal attention feature aggregation. Our network utilizes information from reference frames and target frames to complete the damaged region of the target frame. We first employ motion compensation to align the features of reference frames, and then use the temporal attention module to aggregate these features, resulting in accurate and reasonable content. To evaluate the effectiveness of our method, we introduce a new text video dataset with multiple text objects and complex textures, presenting a novel and challenging task for inpainting research. Through quantitative and qualitative comparison experiments, we demonstrate that our model outperforms existing baseline models in scenarios with multiple objects and complex textures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiclass Brain Tumor Detection using Convolutional Neural Network and Conventional Machine Learning 2

Multiclass Brain Tumor Detection using Convolutional Neural ...

引用

2nd IEEE International Conference on Emerging Research in Computational Science, ICERCS 2024

作者： Vidhya, K. Vamsi Krishna, B. Haritha, M. Rajasekaran, Arun Sekar Roopa Chandrika, R. Velusamy, Jayaraj Karunya Institute of Technology and Sciences Division of Data Science and Cyber Security School of Computer Science and Technology Coimbatore India QIS College of Engineering and Technology Department of AIMLDS Andhra Pradesh India QIS College of Engineering and Technology Department of Mechanical Engineering Andhra Pradesh India SR University Department of Electronics and Communication Engineering Telangana India Karpagam Academy of Higher Education Department of Cyber Security Coimbatore India Nehru Institute of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798331534950

Brain tumor (BT) affect the brain and reduce the lifespan of humans. Therefore, diagnosis and treatment of illnesses in its early stage is required. The objective of this paper is to evaluate the effectiveness of the Convolutional Neural Network (CNN) and Conventional Machine Learning (CML) strategies for identifying multiple classes of brain tumor. In the research, a comparison is made between these two systems for the picture classification of brain tumor. The first step is the collection and preprocessing of images of several classes of brain tumor. The CNN and CML models are trained using the preprocessed dataset. CML makes use of traditional machine learning (ML) algorithms for the purpose of feature extraction and classification, whereas CNN relies on convolutional layers to automatically extract significant features from the images it is fed as input. Precision, accuracy, F1 score, and recall are the criteria that are utilized to evaluate methods. In terms of accuracy and overall performance, CNN is superior to CML. CNN provides a more precise classification of a variety of tumor classifications. Based on these findings, convolutional neural networks (CNN) are likely superior than machine learning for the identification of multiclass brain tumor. CNNs are superior because of their ability to directly understand intricate patterns and characteristics from photographs. This work demonstrates the usefulness of CNNs for multiclass classification in brain tumor detection systems because of their high accuracy and efficiency. © 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

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：