检索结果-内蒙古大学图书馆

12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

作者： Zhao, Minghua Wang, Qin Muniru, Abdul Nasir Ning, Jiawei Li, Peng Li, Bing School of computer science and engineering Xi'an University of Technology Xi'an Shaanxi China Shaanxi Key Laboratory of Network Computing and Security Technology Xi'an Shaanxi China

ISBN: (纸本)9781728148526

Total variation model of image denoising is easy to influence the gradient and lose the details of image. Due to these weaknesses, many adaptive total variation (ATV) models of image denoising have been proposed to eliminate the Gaussian noisy additive in the image. This paper implements the model through a numerical solution, where the gradient descent method is used to derive the partial differential equation (PDE) corresponding to the ATV model. First, based on Euler-Lagrange equation, a detailed derivation process for Partial Differential Equation is used to calculate the ATV model. Then, based on gradient descent method, a numerical calculation of the model is derived from the PDE using the Direct Difference Method. Finally, several different λ parameters are compared to produce different image denoising effects and the appropriate parameter λ value is determined. Experimental results prove that our proposed numerical calculation can effectively realize the ATV denoising model. © 2019 IEEE.

关键词： Partial differential equations

来源：评论

学校读者我要写书评

暂无评论

Dynamic Detection of Malicious Code on Android Based on Improved Multi-feature Gaussian Kernel 15th

Dynamic Detection of Malicious Code on Android Based on Impr...

引用

15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft computing and Applications, ICHSA 2019

作者： Yu, Qing Luo, Xixi Wang, Zuohua Tianjin Key Laboratory of Intelligence Computing and Network Security Tianjin University of Technology Tianjin300384 China China Everbright Bank Co. Ltd. Tianjin300384 China

ISBN: (纸本)9783030325909

In recent years, with the increasing demand for mobile Internet, smartphones represented by the Android system begin to play an increasingly important role in people’s daily life. Due to the payment and social functions of smartphones, users’ property safety and personal privacy are increasingly threatened by malicious mobile apps. Lured by great interests, malicious applications began to spread in the mobile platform, malicious code is escalating, Android-side security is facing great threats. Therefore, it is very important to study the detection of malicious code in Android. This paper studies and analyzes the status of Android malicious code detection. On the basis of dynamic detection, this paper presents a dynamic detection algorithm of multi-feature IGK. The algorithm optimizes feature selection and Gaussian kernel function and applies the improved algorithm to multi-feature training to improve the detection accuracy of malicious code. We track application system calls and system service calls while the system is running, extract features from system call sequences and system service calls. Then we use the improved weighted information gain method to select the features. Finally, in view of the deficiencies of the traditional Gaussian kernel function in recognition rate and processing time, an improved Gaussian kernel function is proposed for machine learning. We evaluated our approach with 800 benign applications and 1200 malicious applications. The experimental results show that by the above two improvements, the highest detection rate is 97.5%, better than the existing methods. © 2020, Springer Nature Switzerland AG.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Cetus: an efficient symmetric searchable encryption against file-injection attack with SGX

引用

Science China(Information Sciences) 2021年第8期64卷 195-212页

作者： Yanyu HUANG Siyi LV Zheli LIU Xiangfu SONG Jin LI Yali YUAN Changyu Dong College of Cyber Science and the College of Computer Science Tianjin Key Laboratory of Network and Data Security TechnologyNankai University School of Computer Science and Technology Shandong University School of Computer Science Guangzhou University Department of Computer Science University of G?ttingen School of Computing Newcastle University

Symmetric searchable encryption(SSE) allows the users to store and query their private data in the encrypted database. Many SSE schemes for different scenarios have been proposed in the past few years, however, most of these schemes still face more or fewer security issues. Using these security leakages,many attacks against the SSE scheme have been proposed, and especially the non-adaptive file injection attack is the most serious. Non-adaptive file injection attack(NAFA) can effectively recover some extremely important private information such as keyword plaintext. As of now, there is no scheme that can effectively defend against such attacks. We first propose the new security attribute called toward privacy to resist nonadaptive file injection attacks. We then present an efficient SSE construction called Cetus to achieve toward privacy. By setting up a buffer and designing the efficient oblivious reading algorithm based on software guard extensions(SGX), we propose the efficient one-time oblivious writing mechanism. Oblivious writing protects the update pattern and allows search operations to be performed directly on the data. The experiment results show that Cetus achieves O(aw) search time and O(1) update communication. The practical search time, communication, and computation overheads incurred by Cetus are lower than those of state-of-the-art.

关键词： searchable encryption SGX technique file injection attack forward/toward privacy cloud databases

来源：评论

学校读者我要写书评

暂无评论

Social Recommendation Combining Implicit Information and Rating Bias

Social Recommendation Combining Implicit Information and Rat...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Weizhi Ying Qing Yu Zuohua Wang Tianjin Key Laboratory of Intelligence Computing and Network Security Tianjin University of Technology Tianjin China China Everbright Bank CO.LTD Beijing China

ISBN: (纸本)9781728165974;9781728165981

In recent years, more and more recommendation algorithm considers social information. However, in the existing social recommendation algorithm focused on the rating prediction task, the user's rating bias and the item's rating bias are often not considered. Besides, the existing social recommendation algorithms usually fail to deal with the sparse problem of social information. Concerning the problem of ignores rating bias and social information sparsity in the social recommendation, this paper proposes a novel recommendation model that combines implicit information and rating bias based on the traditional matrix factorization model. The social information used includes explicit social information and implicit social information generated by collaborative user network embedding methods. Experimental results on two real public datasets show that compared with other recommendation models, the proposed model reduces 1.13% to 10.09% and 3.14% to 8.38% respectively in the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). It shows that our proposed recommendation algorithm has a better recommendation effect.

关键词： Computational modeling Conferences Collaboration Transforms Prediction algorithms Collaborative work Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Edge Data Integrity Verification: Fundamentals and Future Trends

arXiv

引用

arXiv 2022年

作者： Zhao, Yao Qu, Youyang Xiang, Yong Uddin, Md Palash Peng, Dezhong Gao, Longxiang School of Information Technology Deakin University Australia Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science China College of Computer Science Sichuan University China

Recent advances in edge computing (EC) have pushed cloud-based data caching services to edge, however, such emerging edge storage comes with numerous challenging and unique security issues. One of them is the problem of edge data integrity verification (EDIV) which coordinates multiple participants (e.g., data owners and edge nodes) to inspect whether data cached on edge is authentic. To date, various solutions have been proposed to address the EDIV problem, while there is no systematic review. Thus, we offer a comprehensive survey for the first time, aiming to show current research status, open problems, and potentially promising insights for readers to further investigate this under-explored field. Specifically, we begin by stating the significance of the EDIV problem, the integrity verification difference between data cached on cloud and edge, and three typical system models with corresponding inspection processes. To thoroughly assess prior research efforts, we synthesize a universal criteria framework that an effective verification approach should satisfy. On top of it, a schematic development timeline is developed to reveal the research advance on EDIV in a sequential manner, followed by a detailed review of the existing EDIV solutions. Finally, we highlight intriguing research challenges and possible directions for future work, along with a discussion on how forthcoming technology, e.g., machine learning and context-aware security, can augment security in EC. Given our findings, some major observations are: there is a noticeable trend to equip EDIV solutions with various functions and diversify study scenarios;completing EDIV within two types of participants (i.e., data owner and edge nodes) is garnering escalating interest among researchers;although the majority of existing methods rely on cryptography, emerging technology is being explored to handle the EDIV problem. Copyright © 2022, The Authors. All rights reserved.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Research on the Distribution Characteristics of Standardized Big Data Resources Based on Data Visualization——Taking Standardization Practice in Shandong Province as an Example

Research on the Distribution Characteristics of Standardized...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Jinyang Sun Dongdong Peng Zhe Lu Mengran Zhai Ning Qi Yuanhua Qi SHANDONG SCICOM Information and Economy Research Institute Co. Ltd Jinan China Jinan Municipal Bureau of Big Data Jinan China Shandong Institute of Economy and Informatization Development 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

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Standardized big data, as a product of the combination of big data and standardization work, objectively reflects the status quo and trends of standardization work. An in-depth study of the distribution characteristics of standardized big data resources has important value for improving the efficiency of standardization. Therefore, this paper explores the characteristics of the distribution of standardization resources from the dimensions of spatial and temporal distribution, industry distribution, standard type distribution, and distribution of think tank experts through visual analysis methods. The study shows that: (1) the distribution of standardization resources in Shandong Province presents significant hierarchical and geographical characteristics; (2) from the viewpoint of the distribution of industry types and standard types, the distribution of standardization resources in Shandong Province presents a typical "long-tailed distribution"; (3) the distribution of think-tank experts presents obvious "agglomeration effect".

关键词： Industries Technological innovation Heavily-tailed distribution Animals Urban areas Data visualization Forestry Big Data Fisheries Standards

来源：评论

学校读者我要写书评

暂无评论

Graph Learning-Based Multi-User Multi-Task Offloading in Wireless computing Power networks

引用

IEEE Internet of Things Journal 2025年

作者： Dai, Yueyue Rao, Xiaoyang Gu, Bruce Qu, Youyang Yang, Huiran Lu, Yunlong Huazhong University of Science and Technology Research Center of6G Mobile Communications School of Cyber Science and Engineering Wuhan430074 China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education China Australia University of Chinese Academy of Sciences Institute of Information Engineering Chinese Academy of Sciences Beijing China and the School of Cyber Security Beijing China Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China

To enhance service quality, wireless computing power networks (WCPNs) need to realize flexible scheduling and allocation of computation resources across heterogeneous computing servers. Due to large user scales and diverse computation tasks, it is difficult for the current WCPN to serve multiple users and handle multiple tasks concurrently. Graph learning is a promising approach that can learn the representations of nodes through graph structures, enabling the exploration of dependencies among multiple users and tasks, and thereby facilitating computation task offloading. In this paper, we propose a graph learning-based multi-user multi-task offloading scheme for WCPN. First, we propose a wireless computing power network with multi-user and multi-task in which users need to make full use of distributed computing resources through task offloading to ensure efficient task execution. We formulate a system energy consumption minimization problem to jointly optimize computation resources, transmission power, and task offloading. To address the problem, we utilize graph learning to transform the joint optimization problem into a graph regression problem and leverage line graph to explore the solution. Numerical results demonstrate that our proposed scheme can improve computation efficiency, enhance optimization performance, and maintain transferability compared with the benchmarks. © 2014 IEEE.

关键词： computing power

来源：评论

学校读者我要写书评

暂无评论

CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning

arXiv

引用

arXiv 2022年

作者： Shu, Jun Yuan, Xiang Meng, Deyu Xu, Zongben School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi China Peng Cheng Laboratory Guangdong Shenzhen China The Macau Institute of Systems Engineering Macau University of Science and Technology Taipa China

Modern deep neural networks (DNNs) can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require manually pre-specifying the weighting schemes as well as their additional hyper-parameters relying on the characteristics of the investigated problem and training data. This makes them fairly hard to be generally applied in practical scenarios, due to their significant complexities and inter-class variations of data bias situations. To address this issue, we propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data. Specifically, by seeing each training class as a separate learning task, our method aims to extract an explicit weighting function with sample loss and task/class feature as input, and sample weight as output, expecting to impose adaptively varying weighting schemes to different sample classes based on their own intrinsic bias characteristics. Synthetic and real data experiments substantiate the capability of our method on achieving proper weighting schemes in various data bias cases, like the class imbalance, feature-independent and dependent label noise scenarios, and more complicated bias scenarios beyond conventional cases. Besides, the task-transferability of the learned weighting scheme is also substantiated, by readily deploying the weighting function learned on relatively smaller-scale CIFAR-10 dataset on much larger-scale full WebVision dataset. A performance gain can be readily achieved compared with previous state-of-the-art ones without additional hyper-parameter tuning and meta gradient descent step. The general availability of our method for multiple robust deep learning issues, including partial-label learning, semi-supervised learning and selective classification, has also been validated. Code for reproducing our experiments is available at https://github

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Resilient Decentralized Learning Approach against Byzantine Attack via Reputation Evaluation

A Resilient Decentralized Learning Approach against Byzantin...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Heng Zhang Wenting Wang Xuguo Jiao Ming Yang Xiaoming Wu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan P. R. China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan P. R. China College of Control Science and Engineering Zhejiang University Hangzhou China State Grid Shandong Electric Power Research Institute Jinan China School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

Machine learning is a key component of many applications, among which decentralized learning has attracted wide attention because of its cost-effectiveness and high efficiency. However, decentralized learning is vulnerable to various Byzantine attacks. Existing defense models face challenges in defending against complex attacks and are often constrained by strict network topologies. To address this issue, a parameter aggregation rule based on reputation evaluation (RPV) is proposed in this paper. This rule establishes a reputation model for neighboring nodes and continuously updates it based on their distance performance during each iteration. By applying the reputation model of neighboring nodes to the Beta distribution, their reliability is obtained. Based on the reliability of neighboring nodes, the set of reliable nodes for this iteration and select parameter values from them for aggregation are determined. Finally, we gradually eliminate the influence of Byzantine nodes. Our experimental results on the MNIST dataset demonstrate that the proposed algorithm is resilient to attacks from any number of Byzantine nodes and outperforms previous defense models in terms of network topology constraints, training accuracy, and computational costs.

关键词： Training Learning systems Accuracy network topology Computational modeling Machine learning Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Competitive Swarm Optimizer for Multi-task Optimization 2020

Enhanced Competitive Swarm Optimizer for Multi-task Optimiza...

引用

Proceedings of the 2020 9th International Conference on computing and Pattern Recognition

作者： Wei Li Junqing Yuan Haonan Luo Zhou Lei Qingzheng Xu School of Computer Science and Engineering Xi'an University of Technology and Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China School of Computer Science and Engineering Xi'an University of Technology Xi'an China College of Information and Communication National University of Defense Technology Xi'an China

ISBN: (纸本)9781450387835

In the real world, many problems possess the high degree of similarity. Inspired by multifactorial inheritance model, evolutionary multi-task optimization paradigm is proposed to simultaneously solve multiple optimization problems. However, experimental results have revealed that the performance of multifactorial evolutionary algorithm deteriorates with negative knowledge transfer between uncorrelated tasks. To alleviate this issue, we proposed an enhanced competitive swarm optimizer to explore the generality of the multitasking paradigm. A new velocity update mechanism for losers is proposed to improve the search ability. Further, a mating approach is proposed to transfer implicit knowledge among tasks for generating offspring. Experimental and statistical analyses are performed on CEC2017 evolutionary multitask optimization competition. Results show that the proposed algorithm is competitive in comparison with other state-of-the-art multifactorial optimization algorithms.

关键词： Evolutionary multitasking competitive swarm optimizer evolutionary algorithms

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：