检索结果-南通市图书馆

第三届多媒体信息网络与安全国际会议

作者： Jinwei wang Jiangsu Engineering Center of Network Monitoring school of computer and software nanjing university of information science and technology nanjing china 210044Shiguo Lian France Telecom Research and Development (Orange Labs) Beijing Beijing china 10080 leiming yan and yuxiang wang school of computer and software nanjing university of information science and technology nanjing china 210044

With the rapid development and the richer content of the Internet, the copyright protection of the works should be further developed. The watermarking has become a possible solution. In this paper, firstly, a novel hybrid multiplicative rule is presented and utilized to embed the watermark into DWT coefficients controlled by the secret key. Secondly, the optimum and locally optimum hybrid multiplicative multi-watermarking decoders are proposed, respectively, which are based on the minimum Bayesian risk criterion. The DWT coefficients are modeled as the generalized Gaussian distribution. Nextly, the performance of the optimum hybrid watermarking decoder, i.e. the average bit error rate is theoretically analyzed. Then the security of the hybrid multiplicative watermarking scheme is compared with the existing schemes. Finally, experimental results prove the theoretical analysis valid.

关键词： hybrid embedding rule hybrid decoder opti- mum and lcoally optimum

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Survey on Adversarial Examples in Deep Learning

引用

Journal on Big Data 2020年第2期2卷 71-84页

作者： Kai Chen Haoqi Zhu leiming yan Jinwei wang school of computer&software Nanjing University of Information Science&TechnologyNanjing210044China school of Atmospheric sciences Nanjing University of Information Science&TechnologyNanjing210044China

Adversarial examples are hot topics in the field of security in deep *** feature,generation methods,attack and defense methods of the adversarial examples are focuses of the current research on adversarial *** article explains the key technologies and theories of adversarial examples from the concept of adversarial examples,the occurrences of the adversarial examples,the attacking methods of adversarial *** article lists the possible reasons for the adversarial *** article also analyzes several typical generation methods of adversarial examples in detail:Limited-memory BFGS(L-BFGS),Fast Gradient Sign Method(FGSM),Basic Iterative Method(BIM),Iterative Least-likely Class Method(LLC),***,in the perspective of the attack methods and reasons of the adversarial examples,the main defense techniques for the adversarial examples are listed:preprocessing,regularization and adversarial training method,distillation method,etc.,which application scenarios and deficiencies of different defense measures are pointed *** article further discusses the application of adversarial examples which currently is mainly used in adversarial evaluation and adversarial ***,the overall research direction of the adversarial examples is prospected to completely solve the adversarial attack *** are still a lot of practical and theoretical problems that need to be *** out the characteristics of the adversarial examples,giving a mathematical description of its practical application prospects,exploring the universal method of adversarial example generation and the generation mechanism of the adversarial examples are the main research directions of the adversarial examples in the future.

关键词： Adversarial examples generation methods defense methods

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Multi-Label Chinese Comments Categorization: Comparison of Multi-Label Learning Algorithms

引用

Journal of New Media 2019年第2期1卷 51-61页

作者： Jiahui He Chaozhi wang Hongyu Wu leiming yan Christian Lu school of computer and software Nanjing University of Information Science&TechnologyNanjing210044China school of information technology Deakin UniversityVictoriaAustralia

Multi-label text categorization refers to the problem of categorizing text througha multi-label learning algorithm. Text classification for Asian languages such as Chinese isdifferent from work for other languages such as English which use spaces to separate *** classifying text, it is necessary to perform a word segmentation operation to converta continuous language into a list of separate words and then convert it into a vector of acertain dimension. Generally, multi-label learning algorithms can be divided into twocategories, problem transformation methods and adapted algorithms. This work will usecustomer's comments about some hotels as a training data set, which contains labels for allaspects of the hotel evaluation, aiming to analyze and compare the performance of variousmulti-label learning algorithms on Chinese text classification. The experiment involves threebasic methods of problem transformation methods: Support Vector Machine, Random Forest,k-Nearest-Neighbor;and one adapted algorithm of Convolutional Neural Network. Theexperimental results show that the Support Vector Machine has better performance.

关键词： Multi-label classification Chinese text classification problem transformation,adapted algorithms

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

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：