检索结果-内蒙古大学图书馆

Robotics, Intelligent Control and Artificial Intelligence (RICAI), International Conference on

作者： Songtao Wang Qianlong Liu Jun Li Kun Liang Hui Cai Hangwei Tian Shandong Hi-Speed Construction Management Group Co. Ltd. Jinan China SHANDONG SCICOM Information and Economy Research Institute Co. Ltd. Jinan China Shandong Hi-Speed Group Linteng Highway Co. Ltd. Jinan China School of Qilu Transportation Shandong University Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China

In the field of mechanical manufacturing, rolling bearings are important core components. To achieve stable rotational operation, improving diagnostic accuracy has become an urgent issue. In this paper, a hybrid fault diagnosis method is proposed, which combines attention and convolutional neural network and introduces Savitzky-Golay filter, called Savitzky-Golay Convolutional Attention network (SGCA-Net). The method adopts a dual-branch structure for rolling bearing fault diagnosis, which can effectively eliminate noise, and combines attention mechanism and convolutional neural network to perform feature learning on data. The experimental results show that the proposed method can accurately identify various faults, and has high accuracy and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PathAFL: Path-Coverage Assisted Fuzzing 20

PathAFL: Path-Coverage Assisted Fuzzing

引用

15th ACM Asia Conference on Computer and Communications security, ASIA CCS 2020

作者： Yan, Shengbo Wu, Chenlu Li, Hang Shao, Wei Jia, Chunfu Nankai University College of Cyber Science TianJin China Nankai University College of Artificial Intelligence TianJin China Nankai University College of Cyber Science TianJin Key Laboratory of Network and Data Security Technology TianJin300350 China

ISBN: (纸本)9781450367509

Fuzzing is an effective method to find software bugs and vulnerabilities. One of the most useful techniques is the coverage-guided fuzzing, whose key element is the tracing code coverage information. Existing coverage-guided fuzzers generally use the the number of basic blocks or edges explored to measure code coverage. Path-coverage can provide more accurate coverage information than basic block and edge coverage. However, the number of paths grows exponentially as the size of a program increases. It is almost impossible to trace all the paths of a real-world application. In this paper, we propose a fuzzing solution named PathAFL, which assists a fuzzer by path identification. It can effectively identify and utilize the important h-path, which is a new path but whose edges have all been touched previously. First, PathAFL only inserts one assembly instruction to AFL's original code to calculate the path hash, and uses a selective instrumentation strategy to reduce the tracing granularity of an execution path. Second, we design a fast filtering algorithm to choose higher weight paths from a large number of h-paths and add them to the seed queue. Third, both the seed selection algorithm and the power schedule are implemented based on the path weight. Finally we implemented PathAFL based on the popular fuzzer AFL and evaluated it on 10 well-fuzzed benchmark programs. In 24 hours, PathAFL explored 38% more paths and 9.3% more edges than AFL. Compared with CollAFL-x, the number is 25% and 5.9% correspondingly. Moreover, PathAFL found the more bugs on the LAVA-M dataset, even four unlisted bugs. The results show that PathAFL outperforms the previous fuzzers in terms of both code coverage and bug discovery. In well-tested programs, PathAFL found 8 new security bugs with 6 CVEs assigned. © 2020 ACM.

关键词： Program debugging

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Method for Satellite networks Based on Genetic Optimization Federated Learning

引用

Expert Systems with Applications 2025年

作者： Zhimin Wang Jinhui Cao Xiaoqiang Di School of Computer Science and Technology Changchun University of Science and Technology Changchun 130022 China Jilin Province Key Laboratory of Network and Information Security Changchun University of Science and Technology Changchun 130022 China Information Center Changchun University of Science and Technology Changchun 130022 China

Satellite networks are integral to global communications, however, they are increasingly targeted by sophisticated cyber-attacks due to their open-channel nature. Existing machine learning-based anomaly detection methods often fail to jointly model the spatial and temporal dependencies in traffic data, while traditional federated learning approaches suffer from inefficient client selection and privacy vulnerabilities. To address these challenges, this paper proposes FLOGA-AD, a novel federated anomaly detection framework for satellite networks, enhanced with a genetic algorithm for intelligent client selection. The model integrates a hybrid deep learning architecture that combines Convolutional Vision Transformer (CvT) for spatial feature extraction and Long Short-Term Memory (LSTM) for temporal modeling. To ensure both performance and privacy, the system incorporates Differential Privacy and Secure Aggregation during model updates. Extensive experimental evaluations conducted on the UNSW-NB15 and STIN datasets demonstrate that FLOGA-AD achieves performance improvements of 3% and 5%, respectively, over the state-of-the-art deep federated detection framework (DFL-TD). The proposed method effectively enhances anomaly detection accuracy while maintaining rigorous privacy guarantees and significantly reducing both communication bandwidth and computational resource requirements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Deepfake videos using long distance attention

arXiv

引用

arXiv 2021年

作者： Lu, Wei Liu, Lingyi Luo, Junwei Zhao, Xianfeng Zhou, Yicong Huang, Jiwu School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100195 China School of Cyber Security University of Chinese Academy of Sciences Beijing100195 China Department of Computer and Information Science University of Macau 999078 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

With the rapid progress of deepfake techniques in recent years, facial video forgery can generate highly deceptive video contents and bring severe security threats. And detection of such forgery videos is much more urgent and challenging. Most existing detection methods treat the problem as a vanilla binary classification problem. In this paper, the problem is treated as a special fine-grained classification problem since the differences between fake and real faces are very subtle. It is observed that most existing face forgery methods left some common artifacts in the spatial domain and time domain, including generative defects in the spatial domain and inter-frame inconsistencies in the time domain. And a spatial-temporal model is proposed which has two components for capturing spatial and temporal forgery traces in global perspective respectively. The two components are designed using a novel long distance attention mechanism. The one component of the spatial domain is used to capture artifacts in a single frame, and the other component of the time domain is used to capture artifacts in consecutive frames. They generate attention maps in the form of patches. The attention method has a broader vision which contributes to better assembling global information and extracting local statistic information. Finally, the attention maps are used to guide the network to focus on pivotal parts of the face, just like other fine-grained classification methods. The experimental results on different public datasets demonstrate that the proposed method achieves the state-of-the-art performance, and the proposed long distance attention method can effectively capture pivotal parts for face forgery. Copyright © 2021, The Authors. All rights reserved.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

Application of BIM coding and example modelling for typical asphalt pavement diseases based on Omni Class 2

Application of BIM coding and example modelling for typical ...

引用

2nd International Conference on Advanced Materials and Intelligent Manufacturing, ICAMIM 2021

作者： Li, Xian Tong Zhang, Hong Wei Liu, Zhen Zheng Qu, Wan Ying Wu, Zhao Hui Wang, Liang China Academy of Transportation Sciences Beijing100029 China Inner Mongolia Autonomous Region Traffic Construction Engineering Quality Supervision Bureau Hohhot0110051 China Key laboratory of Transport Industry of Management Control and Cycle Repair Technology for Traffic Network Facilitates in Ecological Security Barrier Area Hohhot0110051 China Changchun Municipal Engineering Design and Research Institute Changchun130000 China

With the widespread application of BIM technology in highway engineering, the practice of coding asphalt pavement diseases and integrating it with BIM models in the highway management and maintenance stage can contribute to the clarity of data collection and source-tracing of the disease and strengthening the circulation of disease data in the whole life cycle of highway engineering. This paper compares the coding methods of construction and infrastructure coding at home and abroad, and identifies the disease of asphalt pavement according to existing norms and clarifies the rules for formulating disease coding in the aim of producing a unified coding method of asphalt pavement disease. At the same time, based on the establishment of the disease model, the coding information is integrated with the BIM model to fill in the gaps in the coding work in the management and maintenance of highway engineering to improve the circulation of code-integrated BIM disease model in the maintenance phase. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Asphalt pavements

来源：评论

学校读者我要写书评

暂无评论

A lightweight privacy-preserving scheme using label-based pixel block mixing for image classification in deep learning

arXiv

引用

arXiv 2021年

作者： Xiang, Yuexin Li, Tiantian Ren, Wei Zhu, Tianqing Raymond Choo, Kim-Kwang School of Computer Science China University of Geosciences Wuhan China Henan Key Laboratory of Network Cryptography Technology Zhengzhou China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Department of Information Systems and Cyber Security University of Texas at San Antonio San AntonioTX78249-0631 United States

To ensure the privacy of sensitive data used in the training of deep learning models, a number of privacy-preserving methods have been designed by the research community. However, existing schemes are generally designed to work with textual data, or are not efficient when a large number of images is used for training. Hence, in this paper we propose a lightweight and efficient approach to preserve image privacy while maintaining the availability of the training set. Specifically, we design the pixel block mixing algorithm for image classification privacy preservation in deep learning. To evaluate its utility, we use the mixed training set to train the ResNet50, VGG16, InceptionV3 and DenseNet121 models on the WIKI dataset and the CNBC face dataset. Experimental findings on the testing set show that our scheme preserves image privacy while maintaining the availability of the training set in the deep learning models. Additionally, the experimental results demonstrate that we achieve good performance for the VGG16 model on the WIKI dataset and both ResNet50 and DenseNet121 on the CNBC dataset. The pixel block algorithm achieves fairly high efficiency in the mixing of the images, and it is computationally challenging for the attackers to restore the mixed training set to the original training set. Moreover, data augmentation can be applied to the mixed training set to improve the training’s *** Codes 68T07 Copyright © 2021, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

The theoretical study of Cs/O absorption on Ga0.9375Mg0.0625N (0001) surface: A first principle calculation 10

The theoretical study of Cs/O absorption on Ga0.9375Mg0.0625...

引用

2020 10th International Conference on Applied Physics and Mathematics, ICAPM 2020

作者： Ren, S.S. Ma, J. Fu, X.Q. Yang, M.Z. Zhao, H. School of Information Science and Engineering University of Jinan China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan China School of Physics and Optoelectronic Engineering Nanjing University of Information Science and Technology China

In order to theoretically study the adsorption process of GaN photocathode, the adsorption model on Ga0.9375Mg0.0625N is established. Then, the adsorption energy, work function, mullikeen charge distribution and density of states on the surface of (2 2) Ga0.9375Mg0.0625N(0001)calculate are calculated by first principle on CASTEP. By comparing the adsorption energy of Cs on N atom, surface centrality and Mg atom, the result shows that adsorption is the most stable on Mg atom. The Cs/O absorption model on Mg atom is mainly researched, according to analysis the properties of different computing results for different adsorption models, it is found that they are in accordance with the changing trend of the experiment. This provides a theoretical basis for the study of the experiment. © Published under licence by IOP Publishing Ltd.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Research on the status of industrial sewage equipment based on clustering ensemble

Research on the status of industrial sewage equipment based ...

引用

International Conference on Computational Science and Computational Intelligence (CSCI)

作者： Qinlu Li Tao Du Rui Zhang Jin Zhou Shouning Qu School of Information Science and Engineering University of Jinan Jinan China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China Shandong Management University Jinan China State Key Laboratory of High-end Server and Storage Technology

ISBN: (纸本)9781665458429

The collected industrial data are usually unlabeled, and generally use clustering algorithm for data analysis. However, a single clustering algorithm can not guarantee a good analysis of industrial datasets, and there are many limitations for users. By fusing multiple results obtained by the analysis, clustering ensemble can get more effective results. Therefore, we use density-based selective clustering ensemble method to analysis the collected datasets. The main steps are as follows: (1) use three density based clustering algorithms to analyze the datasets; (2) in order to remove the negative influence of noise, zero the elements in the obtained co-association matrix multiple times, and obtain corresponding results by hierarchical clustering; (3) set the internal validity index to select the best result. Through the experiment and the feedback of relevant factories, the effectiveness of the experiment is proved.

关键词： Data analysis Shape Scientific computing Clustering algorithms Robustness Production facilities Indexes

来源：评论

学校读者我要写书评

暂无评论

An efficient matrix multiplication with enhanced privacy protection in cloud computing and its applications

arXiv

引用

arXiv 2021年

作者： Liu, Chun Hu, Xuexian Chen, Xiaofeng Wei, Jianghong Liu, Wenfen State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Support Force Information Engineering University Zhengzhou450001 China Xidian University China State Key Laboratory of Cryptology P.O. Box 5159 Beijing100878 China Xidian University China and State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Support Force Information Engineering University Zhengzhou450001 China Guangxi Key Laboratory of Cryptogpraphy and Information Security School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

As one of the most important basic operations, matrix multiplication computation (MMC) has varieties of applications in the scientific and engineering community such as linear regression, k-nearest neighbor classification and biometric identification. However handling these tasks with large-scale datasets will lead to huge computation beyond resource-constrained client’s computation power. With the rapid development of cloud computing, outsourcing intensive tasks to cloud server has become a promising method. While the cloud server is generally out of the control of clients, there are still many challenges concerned with the privacy security of clients’ sensitive data. Motivated by this, Lei et al. presented an efficient encryption scheme based on random permutation to protect the privacy of client’s data in outsourcing MMC task. Nevertheless, there exists inherent security flaws in their scheme, revealing the statistic information of zero elements in the original data thus not satisfying the computational indistinguishability (IND-ZEA). Aiming to enhance the security of the outsourcing MMC task, we propose a new encryption scheme based on subtly designed invertible matrix where the additive perturbation is introduced besides the multiplicative perturbation. Furthermore, we show that the proposed encryption scheme can be applied to not only MMC task but also other kinds of outsourced tasks such as linear regression and principal component analysis. Theoretical analyses and experiments indicate that our methods are more secure in terms of data privacy, with comparable performance to the state-of-the-art scheme based on matrix transformation. Copyright © 2021, The Authors. All rights reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Hybrid Encryption System Based on SM2 and SM4 Algorithm

Research and Implementation of Hybrid Encryption System Base...

引用

作者： Zhiqiang Wang Hongyu Dong Yaping Chi Jianyi Zhang Tao Yang Qixu Liu Beijing Electronic Science and Technology Institute State Information Center Key Lab of Information Network Security Ministry of Public Security Key Laboratory of Network Assessment Technology Institute of Information EngineeringChinese Academy of Sciences

In recent years,the mobile platform network communication performance has made significant progress,with an increasingly large user base and market *** the same time,it also brings many problems such as the leakage of sensitive information after the loss of smart phones,the theft and tampering of private *** at the above problems,this paper proposes a hybrid cryptosystem based on the national secret algorithm SM2 and SM4 and its system solution for implementing secure *** asymmetric encryption algorithm SM2 and the symmetric encryption algorithm SM4 are combined to encrypt the key and the plaintext information of the symmetric encryption algorithm to achieve the double encryption *** experimental results show that the system designed in this paper improves the security of information transmission and key sharing.

关键词： Android National secret hybrid algorithm Information encryption Data security Terminal interaction

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：