检索结果-内蒙古大学图书馆

Consumer Electronics and Computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Ji Li Chunxiang Gu Xieli Zhang Xi Chen Wenfen Liu State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China School of Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9781728183190

ISBN: (纸本)9781728183206

The proliferation of illegal information and criminal behavior on anonymous networks arouses the demand for deanonymization attacks on anonymous communication systems. Flow correlation is a common technique for deanonymization attacks, but most related works currently are based on statistical learning models, thus suffering from burdensome artificial feature engineering. In this paper, we design a novel deep learning model AttCorr for flow correlation attacks on Tor. AttCorr takes the raw traffic features of flow pair as input, including packet sizes, flow directions and inter-packet delays, and uses the multi-head attention mechanism to capture the flow information involved in features and the complex nature of noise in Tor. Experiment results show that AttCorr achieves the same level of accuracy as the stateof-the art method of DeepCorr with lower complexity, simpler feature processing and better interpretability.

关键词： Deep learning Training Correlation Statistical learning Telecommunication traffic Feature extraction Delays

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach Featuring Graph-Based Algorithm for Cell Segmentation and Tracking

A Novel Deep Learning Approach Featuring Graph-Based Algorit...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Keliang Zhao Jovial Niyogisubizo Linxia Xiao Yi Pan Dongqing Wei Didi Rosiyadi Yanjie Wei Shenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China College of Computer Science and Control Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory of Microbial Metabolism and School of Life Sciences and Biotechnology Shanghai Jiao Tong University Shanghai China Research Center for Artificial Intelligence and Cybersecurity National Research and Innovation Agency Bandung Indonesia

The precise segmentation and tracking of cells in microscopy image sequences play a pivotal role in biomedical research, facilitating the study of tissue, organ, and organism development. However, manual segmentation and tracking of cells is time-consuming and often require professional experiences. Besides, segmenting cells in the images with a low signal-to-noise ratio remains difficult. While deep learning (DL) has become a common method for cell segmentation, few DL- based methods address concurrent cell segmentation and tracking. In this paper, we propose a novel DL approach featuring graph-based tracking for cell segmentation and tracking in microscopy images. We combine Deeplabv3+ for semantic segmentation and ResNet50 for enhanced feature extraction, enabling comprehensive cell detection and instance segmentation. Post-processing, involving non-maxima suppression and outlier detection, refines predictions and produces final segmentation. The tracking method is based on the relative position of graph nodes to track segmented cells, encompassing cell division and apoptosis. We conduct our experiments on the induced pluripotent stem (iPS) cell datasets, and the results show that the segmentation and tracking performance of our method yields superior performance compared to the benchmark models. More specifically, our approach achieved DET values of 0.955 and 0.913, TRA values of 0.951 and 0.906, and SEG values of 0.690 and 0.665 on two iPS dataset videos, respectively. Additionally, the performance assessment encompasses four real microscopy datasets from the Cell Tracking Challenge (CTC). Our method greatly reduces the cost of manual labeling and labor-intensive costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pre-ictal causal connectivity reveals the epileptic network characteristics for deep brain stimulation

引用

Neuroscience 2025年 579卷 329-343页

作者： Yifan Wang Tao Yu Yulan Ma Weigang Cui Xueyuan Wang Liankun Ren Yang Li Department of Automation Science and Electrical Engineering Beihang University Beijing 100191 China Beijing Institute of Functional Neurosurgery Department of Functional Neurosurgery Xuanwu Hospital Capital Medical University Beijing 100053 China School of Engineering Medicine Beihang University Beijing 100191 China Department of Neurology Xuanwu Hospital Capital Medical University Beijing 100053 China Beijing Advanced Innovation Center for Big Data and Brain Computing State Key Laboratory of Virtual Reality Technology and Systems Department of Automation Science and Electrical Engineering Beihang University Beijing 100191 China

Deep brain stimulation of anterior nucleus of the thalamus (ANT-DBS) is an effective clinical treatment for drug-resistant focal epilepsy. However, the complex epileptic network characteristics underlying ANT-stimulation effectiveness remain unknown, owing to currently unclear connectivity between ANT and seizure-related cortex in pre-ictal periods. Here, we developed a novel individualized pre-ictal ANT-cortical tripartite connectivity network (PANT-CTCNet), aiming to reveal epileptic network characteristics using intracranial stereo-electroencephalography (sEEG) recordings in five patients with focal epilepsy for 90 trials. Each trial represented a pre-ictal or post-stimulus sEEG duration, which was used to construct the epileptic network. By employing conditional Granger causality, we constructed individualized ANT-cortical connectivity networks and found a common epileptic network centred on ANT closely connected with seizure-related cortex in pre-ictal periods. After ANT stimulation for clinical validation, strengthened pre-ictal connectivity between ANT and epileptogenic zones led to significant decline in the causal intensity of epileptic networks. The PANT-CTCNet can give a quantitative reference for clinical preoperative evaluation of patient suitability for ANT-DBS treatment. These findings regarding epileptic network characteristics provide theoretical basis in the selection of optimal surgical candidates for personalized ANT-DBS.

关键词： Anterior nucleus of the thalamus Epilepsy Epileptic network characteristics Neuromodulation Stereo-electroencephalography

来源：评论

学校读者我要写书评

暂无评论

LEFV: A Lightweight and Efficient System for Face Verification with Deep Convolution Neural Networks 19

LEFV: A Lightweight and Efficient System for Face Verificati...

引用

Proceedings of the 3rd International Conference on Video and Image Processing

作者： Ming Liu Ping Zhang Qingbao Li Jinjin Liu Zhifeng Chen State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781450376822

The emergence of deep learning has made great progress in face recognition. With the popularization of embedded devices, deploying the deep model on embedded devices has become a trend. Most high-precision models require lots of computation costs. Therefore, developing a lightweight deep face recognition system running on embedded devices is a hot topic in current research. To achieve high-accuracy real-time performance of an embedded device, we now present a simple and effective face recognition system LEFV, including face detection, face normalization and face recognition. The quantitative experiments on two large-scale challenging datasets, WIDER FACE dataset and IJB-A dataset, show competitive performances on both runtime and accuracy.

关键词： Face Verification Face Detection Deep Convolution Neural Networks Lightweight Model

来源：评论

学校读者我要写书评

暂无评论

Efficient Low-Resolution Face Recognition via Bridge Distillation

arXiv

引用

arXiv 2024年

作者： Ge, Shiming Zhao, Shengwei Li, Chenyu Zhang, Yu Li, Jia The Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China SenseTime Group Limited 100084 China The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China The Peng Cheng Laboratory Shenzhen518055 China

Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability. In this paper, we propose a bridge distillation approach to turn a complex face model pretrained on private high-resolution faces into a light-weight one for low-resolution face recognition. In our approach, such a cross-dataset resolution-adapted knowledge transfer problem is solved via two-step distillation. In the first step, we conduct cross-dataset distillation to transfer the prior knowledge from private high-resolution faces to public high-resolution faces and generate compact and discriminative features. In the second step, the resolution-adapted distillation is conducted to further transfer the prior knowledge to synthetic low-resolution faces via multi-task learning. By learning low-resolution face representations and mimicking the adapted high-resolution knowledge, a light-weight student model can be constructed with high efficiency and promising accuracy in recognizing low-resolution faces. Experimental results show that the student model performs impressively in recognizing low-resolution faces with only 0.21M parameters and 0.057MB memory. Meanwhile, its speed reaches up to 14,705, 934 and 763 faces per second on GPU, CPU and mobile phone, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Software Supply Chain Analysis Based on Function Similarity

Software Supply Chain Analysis Based on Function Similarity

引用

作者： Wenjie Sun Zheng Shan Fudong liu Xingwei Li Meng Qiao Chunyan Zhang State Key Laboratory of Mathematical Engineering and Advanced Computing

The supply of open source and open source components is growing at an alarming rate,while vulnerabilities in open source components are *** supply chain analysis aims to discover third-party components and open source code used in a software,and analyze the software's dependence on *** this paper,we propose a software component analysis method and a known vulnerabilities detecting *** scanning the open source components of the binary file and conducting vulnerability analysis,the known vulnerabilities are *** paper mainly solves the problem of detecting known vulnerabilities in the supply chain of binary *** conducted a case analysis and achieved good results.

关键词： OpenSSL Software Supply Chain Analysis Based on Function Similarity

来源：评论

学校读者我要写书评

暂无评论

Ultra-Fast Mini License Plate Recognition System Based-on Vision Processing Unit 2

Ultra-Fast Mini License Plate Recognition System Based-on Vi...

引用

2nd International Conference on Big-Data Service and Intelligent Computation, BDSIC 2020

作者： Wang, Junhui Ren, Shuangyin He, Jiezhong Ji, Xiaolan Huang, Diqing College of Computer National University of Defense Technology State Key Laboratory of Mathematical Engineering and Advanced Computing China College of Computer National University of Defense Technology

ISBN: (纸本)9781450388399

As more embedded environments need license plate recognition systems, how to recognize car plates with high speed/accuracy and low energy has become an important and challenging problem. In this paper, we propose a ultra-Fast miNi (FaNi) license plate recognition (LPR) system. The FaNi system are divided into one training sub-system and one inference sub-system. The former are used to get some offline features;then, the latter is deployed online to recognize license numbers with nearly real-time speed. The inference system is comprised of the vision processing unit (VPU) and the display unit. These two parts are both implemented with hardware logic. Experiments show that the FaNi system can obtain high accuracy and high speed with low resource cost. © 2020 ACM.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

NAS Honeypot Technology Based on Attack Chain

NAS Honeypot Technology Based on Attack Chain

引用

作者： Bing Liu Hui Shu Fei Kang State Key Laboratory of Mathematical Engineering and Advanced Computing

With the wide application of network attached storage(NAS), the security problem is becoming more and more serious, together with the increasingly fierce attacks against NAS devices of different manufacturers. In order to better capture various types of attacks against NAS devices and detect security threats in time, this paper proposes a solution named NAS honeypot,mining the potential security threats through modeling and analyzing the NAS threats. Then a NAS honeypot based on device virtualization technology and depth monitoring and attack induction was designed on the basis of the construction NAS attack chain. Experimental results show that the NAS honeypot can effectively capture, record and analyze network attacks against multi-types NAS devices with a strong guiding effect in mastering popular attack method of NAS devices and alleviating the security threats of NAS.

关键词： NAS Threat modeling Attack chain Honeypot

来源：评论

学校读者我要写书评

暂无评论

Field-tuned magnetic structure and phase diagram of the honeycomb magnet YbCl_(3)

引用

Science China(Physics,Mechanics & Astronomy) 2021年第3期64卷 84-89页

作者： YiQing Hao HongLiang Wo YiMeng Gu XiaoWen Zhang YiQing Gu ShiYi Zheng Yang Zhao GuangYong Xu Jeffrey WLynn Kenji Nakajima Naoki Murai WenBin Wang Jun Zhao State Key Laboratory of Surface Physics and Department of Physics Fudan UniversityShanghai 200433China NIST Center for Neutron Research National Institute of Standards and TechnologyGaithersburg 20899USA Department of Materials Science and Engineering University of MarylandCollege Park 20742USA J-PARC Center Japan Atomic Energy Agency(JAEA)Ibaraki 319-1195Japan Institute of Nanoelectronic Devices and Quantum Computing Fudan UniversityShanghai 200433China Collaborative Innovation Center of Advanced Microstructures Nanjing 210093China

We report thermodynamic and neutron diffraction measurements on the magnetic ordering properties of the honeycomb lattice magnet YbCl_(3). We find YbCl_(3) exhibits a Ne′el type long-range magnetic order at the wavevector(0, 0, 0) below TN= 600 *** magnetic order is associated with a small sharp peak in heat capacity and most magnetic entropy release occurs above the magnetic ordering temperature. The magnetic moment lies in-plane, parallel to the monoclinic a-axis, whose magnitude mYb= 0.86(3) μBis considerably smaller than the expected fully ordered moment of 2.24 μBfor the doublet crystal-field ground state. The magnetic ordering moment gradually increases with increasing magnetic field perpendicular to the ab-plane, reaching a maximum value of 1.6(2) μBat 4 T, before it is completely suppressed above ~ 9 T. These results indicate the presence of strong quantum fluctuations in YbCl_(3).

关键词： magnetic order neutron diffraction honeycomb lattice

来源：评论

学校读者我要写书评

暂无评论

Research on the Protection Mechanism of Cisco IOS Exploit

Research on the Protection Mechanism of Cisco IOS Exploit

引用

作者： Jinzhu Wang Ruijie Cai Shengli Liu State Key Laboratory of Mathematical Engineering and Advanced Computing

Cisco IOS is an operating system that runs on Cisco routing and switching *** security is important to the entire *** vulnerability attacks have become one of the main sources of threat to Cisco IOS security,it is necessary to analyze the defense mechanism of IOS against vulnerability *** purpose of this paper is to find out the deficiencies of IOS vulnerability defense mechanism in time and put forward improvement methods and preventive ***,this paper introduces the protection mechanism of Cisco IOS vulnerability,including CheckHeaps,DEP,*** principle of these mechanisms and the idea of vulnerability protection are *** then,after analyzing the shortcomings of these protection mechanisms,the basic idea of bypassing these protection mechanisms is ***,in view of the shortcomings of Cisco IOS vulnerability defense mechanism and the proposed bypass methods,some advices about how to better protect Cisco IOS from vulnerability exploitation are given.

关键词： Research on the Protection Mechanism of Cisco IOS Exploit Cisco IOS

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：