检索结果-内蒙古大学图书馆

Cryptography, Security and Privacy (CSP), IEEE International Conference on

作者： Yan Zheng Weiyu Dong Jiangtao Zhao State Key Laboratory of Mathematical Engineering and Advanced Computing ZhengZhou China

ISBN: (数字)9781728186214

ISBN: (纸本)9781728186221

Docker image is the foundation for container operation. Docker Hub is the largest online repository of public container images. Users can upload and download any random image file to the hub due to the absence of adequate security scanning and detection, potentially causing substantial security risks. This paper introduces ZeroDVS, a container image traceability and security detection system based on inheritance graphs. In ZeroDVS, a basic image inheritance graph is built with 160 official images published by Docker Hub. Then, the basic image source of the downloaded image can be identified, and the public vulnerability database is used to scan for public vulnerabilities in image files. ZeroDVS scans the public container images of Docker Hub and identifies the inheritance relationship of public container images to detect public vulnerabilities in the image layer above the parent image simultaneously. Docker image is the foundation for container operation. Docker Hub is the largest online repository of public container images. Users can upload and download any random image file to the hub due to the absence of adequate security scanning and detection, potentially causing substantial security risks. This paper introduces ZeroDVS, a container image traceability and security detection system based on inheritance graphs. In ZeroDVS, a basic image inheritance graph is built with 160 official images published by Docker Hub. Then, the basic image source of the downloaded image can be identified, and the public vulnerability database is used to scan for public vulnerabilities in image files. ZeroDVS scans the public container images of Docker Hub and identifies the inheritance relationship of public container images to detect public vulnerabilities in the image layer above the parent image simultaneously.

关键词： Privacy Databases Operating systems Containers Security Reliability Cryptography

来源：评论

学校读者我要写书评

暂无评论

ThicknesVAE: Learning a Latera Prior for Clothed Human Body Reconsuction

ThicknesVAE: Learning a Latera Prior for Clothed Human Body ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wu, Xiaotao Fan, Zhaoxin He, Huiguang Shen, Dinggang School of Biomedical Engineering State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University Shanghai201210 China NeuBCI Group State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Institute of Automation Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Institute of Artificial Intelligence Beihang University Beijing100191 China Beijing Academy of Blockchain and Edge Computing China Shanghai United Imaging Intelligence Co. Ltd. Shanghai200232 China Shanghai Clnical Research and Trial Center Shanghai201210 China

ISBN: (纸本)9798350368741

Sandwich-like structures have shown remarkable efficacy in clothed human reconstruction. However, these approaches often generate unrealistic side geometries due to inadequate handling of lateral regions. This paper addresses this limitation by incorporating the side geometry of clothed humans as a prior. We propose ThicknessVAE, a novel two-stage method that makes two key contributions: (1) We learn a prototype from point clouds for the lateral regions of clothed humans to extract common and detailed geometric features. (2) We utilize this prototype as a prior to transform geometric features into a thickness map associated with clothed human images, enabling refined normal integration for sandwich-like reconstruction methods. By seamlessly integrating our model into the sandwich-like reconstruction pipeline, we achieve highly realistic side views. Both qualitative and quantitative experiments demonstrate that our approach is comparable to state-of-the-art methods in terms of side-view realism. © 2025 IEEE.

关键词： 3D Human Reconsruction Normal Integraton Prior Learning

来源：评论

学校读者我要写书评

暂无评论

mathematical modeling of lunar soft landing —Take chang'e-3 as an example

Mathematical modeling of lunar soft landing —Take chang'e-3...

引用

IEEE International Conference on Automation, Electronics and Electrical engineering (AUTEEE)

作者： Benchao Yang State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665428408

In this paper, the three-dimensional sphere dynamic model of lunar precise soft landing of the probe is discussed. Taking the National College Students' mathematical modeling competition as the background and Chang'e 3 lunar landing as an example, the lunar center inertial coordinate system and orbital coordinate system are established respectively to better describe the positional relationship between the moon and aircraft and the dynamic changes of aircraft. The coordinates of the near lunar point and the far lunar point are obtained. Through the changes of altitude, speed, pitch angle, yaw angle, longitude and latitude during landing, the landing preparation orbit of Chang'e-3 is determined. Then we analyze the six stages of chang'e-3 landing process one by one, and discuss the results.

关键词： Space vehicles Machine learning algorithms Moon Clustering algorithms mathematical models Data models Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel Feature Selection Strategy Based on Salp Swarm Algorithm for Plant Disease Detection

引用

Plant Phenomics 2023年第2期5卷 209-225页

作者： Xiaojun Xie Fei Xia Yufeng Wu Shouyang Liu Ke Yan Huanliang Xu Zhiwei Ji College of Artificial Intelligence Nanjing Agricultural UniversityNanjingJiangsu 210095China Center for Data Science and Intelligent Computing Nanjing Agricultural UniversityNanjingJiangsu 210095China State Key Laboratory for Crop Genetics and Germplasm Enhancement Bioinformatics CenterAcademy for Advanced Interdisciplinary StudiesNanjing Agricultural UniversityNanjingJiangsu 210095China Academy for Advanced Interdisciplinary Studies Nanjing Agricultural UniversityNanjingJiangsu 210095China Department of the Built Environment College of Design and EngineeringNational University of Singapore4 Architecture DriveSingapore 117566Singapore

Deep learning has been widely used for plant disease recognition in smart agriculture and has proven to be a powerful tool for image classification and pattern ***,it has limited interpretability for deep *** the transfer of expert knowledge,handcrafted features provide a new way for personalized diagnosis of plant ***,irrelevant and redundant features lead to high *** this study,we proposed a swarm intelligence algorithm for feature selection[salp swarm algorithm for feature selection(SSAFS)]in image-based plant disease *** is employed to determine the ideal combination of handcrafted features to maximize classification success while minimizing the number of *** verify the effectiveness of the developed SSAFS algorithm,we conducted experimental studies using SSAFS and 5 metaheuristic *** evaluation metrics were used to evaluate and analyze the performance of these methods on 4 datasets from the UCI machine learning repository and 6 plant phenomics datasets from *** results and statistical analyses validated the outstanding performance of SSAFS compared to existing state-of-the-art algorithms,confirming the superiority of SSAFS in exploring the feature space and identifying the most valuable features for diseased plant image *** computational tool will allow us to explore an optimal combination of handcrafted features to improve plant disease recognition accuracy and processing time.

关键词： Plant image redundant

来源：评论

学校读者我要写书评

暂无评论

SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints

arXiv

引用

arXiv 2024年

作者： Sheng, Ziqi Lu, Wei Luo, Xiangyang Zhou, Jiantao Cao, Xiaochun School of Computer Science and Engineering MoE Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University China State Key Laboratory of Mathematical Engineering and Advanced Computing China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China School of Cyber Science and Technology Sun Yat-sen University Shenzhen Campus China

Image forgery localization (IFL) is a crucial technique for preventing tampered image misuse and protecting social safety. However, due to the rapid development of image tampering technologies, extracting more comprehensive and accurate forgery clues remains an urgent challenge. To address these challenges, we introduce a novel information-theoretic IFL framework named SUMI-IFL that imposes sufficiency-view and minimality-view constraints on forgery feature representation. First, grounded in the theoretical analysis of mutual information, the sufficiency-view constraint is enforced on the feature extraction network to ensure that the latent forgery feature contains comprehensive forgery clues. Considering that forgery clues obtained from a single aspect alone may be incomplete, we construct the latent forgery feature by integrating several individual forgery features from multiple perspectives. Second, based on the information bottleneck, the minimality-view constraint is imposed on the feature reasoning network to achieve an accurate and concise forgery feature representation that counters the interference of task-unrelated features. Extensive experiments show the superior performance of SUMI-IFL to existing state-of-the-art methods, not only on in-dataset comparisons but also on cross-dataset comparisons. © 2024, CC BY-NC-ND.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

A Partial-Lifting-Based Compiling Concolic Execution Approach

A Partial-Lifting-Based Compiling Concolic Execution Approac...

引用

Cryptography, Security and Privacy (CSP), IEEE International Conference on

作者： Haotian Zhang Weiyu Dong Jian Lin State Key Laboratory of Mathematical Engineering and Advanced Computing ZhengZhou China

ISBN: (数字)9781728186214

ISBN: (纸本)9781728186221

It has been a common phenomenon that embedded devices are used ubiquitously while the security of proprietary software running on devices has become more and more significant. These softwares are often presented to researchers in binary forms. Due to the lack of program semantics and meta information, it is very difficult to analyze manually in large-scale binary programs. Therefore, automatic binary program analysis has become a critical research direction. Symbolic execution is an important method of automatic analysis, due to the problem of path explosion in traditional symbolic execution, it is sometimes complecated to explore the deep-level path of the program, and the most of current execution engines using IR translation execution, resulting in symbolic execution velocity has been exceedingly restrained, comparing to native execution. To this end, we propose a binary program oriented partial-lifting-based compile concolic execution approach, which is combined with static analysis to dissect the binary parts that researchers are intrigued in. The program is simultaneously combined with semantic lifting, dynamic memory monitoring, and symbolic compiler to reconstruct it into a symbolic binary program. Users can perform concolic execution on this program repeatly, so as to explore the part of the original binary program at a rate close to native execution.

关键词： Strips Privacy Program processors Semantics Static analysis Software Engines

来源：评论

学校读者我要写书评

暂无评论

Research on security assessment based on big data and multi-entity profile

Research on security assessment based on big data and multi-...

引用

IEEE advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Wenfu Liu Jianmin Pang Shudan Yang Nan Li Qiming Du Daozhu Sun Fudong Liu State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

Security assessment is one of the important problems, especially in the fields of military training, transportation and network management. The security "related parties" (entities in this paper) have internal relations in the three fields. It is of great significance of constructing the attributes of these entities or even designing a unified security assessment method. Security assessment in these areas has been studied and explored for a long time. However, the research is relatively scattered and unilateral. It is no unified and reusable method from data collection to security assessment. Based on the advantages of big data technology in the storage and analysis of massive data, the paper proposed a security risk element acquisition method from data collection and preprocessing, storage and mining to attribute extraction and aggregation. In addition, drawing on the idea of user portraits in other fields, constructed personnel entities, equipment entities and "other" entity labels related to security risks. Finally, a security risk assessment process based on these entities is designed.

关键词： Training Transportation Big Data Security Personnel Data mining Risk management

来源：评论

学校读者我要写书评

暂无评论

Molecular Dynamics Study of the Effect of Substrate Temperature on the Barrier Behavior in Aluminum Oxide Josephson Junctions

SSRN

引用

SSRN 2022年

作者： Han, Chuanbing Sun, Huihui Hou, Chaofeng Qiu, Junling Wang, Weilong Liu, Fudong Shan, Zheng State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China Institute of Process Engineering Chinese Academy of Sciences Beijing100190 China

Although the quality and reliability of Josephson junctions have improved considerably, the effect of preparation parameters on the structure and nanochemical properties of the barrier layer remains elusive. Here, we use molecular dynamics to study the relationship between the structure and morphology of tunnel barriers and the substrate temperature. We find that substrate temperature affects the atomic arrangement of the barrier, especially in the lower interface region. We also confirm the importance of the lower interface for studying the properties of Josephson junctions and the uncontrollable properties of aluminum oxidation. This work will improve the Josephson junction physical vapor deposition process and lead to the development of a lower noise and more reliable quantum computer. © 2022, The Authors. All rights reserved.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Integrating KNN and Gradient Boosting Decision Tree for Recommendation

Integrating KNN and Gradient Boosting Decision Tree for Reco...

引用

IEEE advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Qiming Du Nan Li Shudan Yang Daozhu Sun Wenfu Liu State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

As an efficient information filtering tool, the recommendation system can help users obtain valuable information quickly and efficiently while effectively alleviating the information load problem. However, the classic collaborative filtering algorithm has data sparsity problems in practical applications, which affects the accuracy of recommendation. To solve this problem, this paper took movie recommendation as the research object and proposed a hybrid recommendation algorithm named K-GBDT which combined KNN and gradient boosting decision tree. Firstly, it used KNN to obtain the similar information of the target user and item for preliminary prediction. At the same time, it mined users' basic information features and potential features of users and items from the original data. Then, it tried to adopt XGBoost, LightGBM and CatBoost algorithm which were proposed base the idea of gradient boosting decision tree to build regression model. Finally, the target user's rating for the movie was predicted with the trained model, and the recommendation list was generated based on the predicted results. Compared with some classic recommendation algorithms such as NMF, Slope One, Co-Clustering and etc. Based on MovieLens datasets, results show that the mean absolute error and root mean square error of this algorithm are both low, and its recommendation accuracy is higher.

关键词： Training Distributed databases Prediction algorithms Boosting Feature extraction Motion pictures Data models

来源：评论

学校读者我要写书评

暂无评论

Expert with Outlier Exposure for Continual Learning of New Diseases

Expert with Outlier Exposure for Continual Learning of New D...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Xu, Zhengjing Chen, Kanghao Zheng, Wei-Shi Tan, Zhijun Yang, Xiaobo Wang, Ruixuan Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE China State Key Laboratory of Dampness Syndrome of Chinese Medicine Guangzhou China Peng Cheng Laboratory Department of Network Intelligence Shenzhen China

ISBN: (纸本)9781665468190

Current intelligent diagnosis systems struggle to continually learn to diagnose more and more diseases due to catastrophic forgetting of old knowledge when learning new knowledge. Although storing small old data for subsequent continual learning can effectively help alleviate the forgetting issue, the heavy data imbalance between old classes and to-be-learned new classes in classifier training often causes biased prediction towards the new classes just learned by the updated classifier. In this study, an outlier detection technique is novelly applied to train an additional expert classifier for new classes to help alleviate the class imbalance issue and discriminate the learned new classes from old classes during inference (instead of the training phase). Specially, the stored small data of old classes are considered as outliers during training the expert classifier, such that the output probability distributions from the expert classifier are expected to be obviously different between test data of the old classes and those of the new classes. Such difference between old classes and new classes can be used to fine-tune the original output from the updated classifier which is responsible for prediction of all learned (old and new) classes. During inference, a novel ensemble strategy is proposed to combine the predictions from the updated classifier, the expert classifier, and the previously learned old classifier. The proposed learning and inference framework can be easily combined with existing continual learning strategies. Empirical evaluations on three medical image datasets and one natural image dataset show that the proposed framework can effectively improve continual learning performance. © 2022 IEEE.

关键词： Forecasting

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：