检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

118 篇 会议
6 册 图书
5 篇 期刊文献

馆藏范围

129 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

105 篇 工学
- 101 篇 计算机科学与技术...
- 11 篇 软件工程
- 8 篇 信息与通信工程
- 6 篇 电气工程
- 4 篇 电子科学与技术（可...
- 2 篇 安全科学与工程
- 1 篇 光学工程
- 1 篇 动力工程及工程热...
- 1 篇 控制科学与工程
- 1 篇 建筑学
- 1 篇 土木工程
- 1 篇 测绘科学与技术
- 1 篇 生物医学工程（可授...
- 1 篇 网络空间安全
39 篇 理学
- 31 篇 统计学（可授理学、...
- 16 篇 数学
- 2 篇 系统科学
- 1 篇 物理学
5 篇 管理学
- 3 篇 图书情报与档案管...
- 2 篇 管理科学与工程(可...
- 1 篇 工商管理
4 篇 法学
- 4 篇 社会学
1 篇 医学
- 1 篇 基础医学(可授医学...
- 1 篇 临床医学
- 1 篇 药学(可授医学、理...

主题

20 篇 differential pri...
18 篇 statistical disc...
15 篇 privacy
13 篇 data privacy
13 篇 synthetic data
11 篇 confidentiality
6 篇 statistical disc...
4 篇 data utility
4 篇 cell suppression
3 篇 clustering
3 篇 tabular data
3 篇 computers and so...
3 篇 privacy-preservi...
3 篇 statistics
3 篇 microaggregation
3 篇 database managem...
3 篇 disclosure contr...
3 篇 official statist...
3 篇 controlled tabul...
3 篇 additive noise

机构

3 篇 natl ctr hlth st...
3 篇 inst employment ...
3 篇 penn state univ ...
3 篇 umea univ dept c...
2 篇 univ politecn ca...
2 篇 ctr wiskunde & i...
2 篇 urban inst washi...
2 篇 csiro computat i...
2 篇 georgia southern...
2 篇 eurecom biot
2 篇 univ rovira & vi...
2 篇 stat netherlands...
2 篇 off natl stat ti...
2 篇 department of co...
2 篇 univ politecn ca...
2 篇 rovira i virgili...
2 篇 rti int res tria...
2 篇 univ lancaster l...
2 篇 karlsruhe inst t...
2 篇 internal revenue...

作者

13 篇 domingo-ferrer j...
6 篇 muralidhar krish...
5 篇 oganian anna
5 篇 josep domingo-fe...
4 篇 castro jordi
4 篇 sanchez david
4 篇 vilhuber lars
3 篇 slavkovic aleksa...
3 篇 ruggles steven
3 篇 drechsler joerg
3 篇 ruiz nicolas
3 篇 blanco-justicia ...
3 篇 lesaja goran
3 篇 torra vicenc
3 篇 giessing sarah
3 篇 iacob ionut
2 篇 mccaa robert
2 篇 onen melek
2 篇 zari oualid
2 篇 charest anne-sop...

语言

128 篇 英文
1 篇 中文

检索条件"任意字段=International Conference on Privacy in Statistical Databases, PSD 2022"

共 129 条记录，以下是31-40 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Synthetic Individual Income Tax Data: Methodology, Utility, and privacy Implications

Synthetic Individual Income Tax Data: Methodology, Utility, ...

引用

international conference on privacy in statistical databases (psd)

作者： Bowen, Claire McKay Bryant, Victoria Burman, Leonard Czajka, John Khitatrakun, Surachai MacDonald, Graham McClelland, Robert Mucciolo, Livia Pickens, Madeline Ueyama, Kyle Williams, Aaron R. Wissoker, Doug Zwiefel, Noah Urban Inst Washington DC 20024 USA Internal Revenue Serv Washington DC 20002 USA Coiled New York NY 10018 USA UCL London England

ISBN: (纸本)9783031139451;9783031139444

The United States Internal Revenue Service Statistics of Income (SOI) Division possesses invaluable administrative tax data from individual income tax returns that could vastly expand our understanding of how tax policies affect behavior and how those policies could be made more effective. However, only a small number of government analysts and researchers can access the raw data. The public use file (PUF) that SOI has produced for more than 60 years has become increasingly difficult to protect using traditional statistical disclosure control methods. The vast amount of personal information available in public and private databases combined with enormous computational power create unprecedented disclosure risks. SOI and researchers at the Urban Institute are developing synthetic data that represent the statistical properties of the administrative data without revealing any individual taxpayer information. This paper presents quality estimates of the first fully synthetic PUF and shows how it performs in tax model microsimulations as compared with the PUF and the confidential administrative data.

关键词： Disclosure control Synthetic data Utility Classification and regression trees

来源：评论

学校读者我要写书评

暂无评论

Synthetic Decimal Numbers as a Flexible Tool for Suppression of Post-published Tabular Data

Synthetic Decimal Numbers as a Flexible Tool for Suppression...

引用

international conference on privacy in statistical databases (psd)

作者： Langsrud, Oyvind Bovelstad, Hege Marie Stat Norway POB 8131 Dept N-0033 Oslo Norway

ISBN: (纸本)9783031139451;9783031139444

Cell suppression is a widely used statistical disclosure control method for tabular data. Commonly, several linked tables are suppressed simultaneously. After publication, additional tables may be requested. In many contexts, new tables mean new ways of grouping and aggregating data that has already been published. The suppression of the new tables must be coordinated with the tables that have already been disseminated. A certain type of synthetic decimal numbers has proven to be very useful for this purpose. Based on the aggregation of these decimal numbers, one can decide whether a cell should be suppressed or not. An aggregation summing up to a whole number means the same as non-suppression. This article describes the theoretical basis for such decimal numbers. This is based on standard methodology from ordinary linear regression. The method is illustrated by a small example. In addition, two practical applications at Statistics Norway are presented, where one involves large hierarchical and linked tables where more than 50000 unique cells were primarily suppressed.

关键词： statistical disclosure control Confidentiality Tabular data Cell suppression Synthetic data Linear regression Official statistics

来源：评论

学校读者我要写书评

暂无评论

Asking the Proper Question: Adjusting Queries to statistical Procedures Under Differential privacy

Asking the Proper Question: Adjusting Queries to Statistical...

引用

international conference on privacy in statistical databases (psd)

作者： Shoham, Tomer Rinott, Yosef Hebrew Univ Jerusalem Dept Comp Sci Jerusalem Israel Hebrew Univ Jerusalem Federmann Ctr Study Rational Jerusalem Israel Hebrew Univ Jerusalem Dept Stat Jerusalem Israel

ISBN: (纸本)9783031139451;9783031139444

We consider a dataset S held by an agency, and a vector query of interest, f(S) is an element of R-k, to be posed by an analyst, which contains the information required for some planned statistical inference. The agency will release an answer to the queries with noise that guarantees a given level of Differential privacy using the well-known Gaussian noise addition mechanism. The analyst can choose to pose the original vector query f(S) or to transform the query and adjust it to improve the quality of inference of the planned statistical procedure, such as the volume of a confidence interval or the power of a given test of hypothesis. Previous transformation mechanisms that were studied focused on minimizing certain distance metrics between the original query and the one released without a specific statistical procedure in mind. Our analysis takes the Gaussian noise distribution into account, and it is non-asymptotic. In most of the literature that takes the noise distribution into account, a given query and a given statistic based on the query are considered and the statistic's asymptotic distribution is studied. In this paper we consider both non-random and random datasets, that is, samples, and our inference is on f(S) itself, or on parameters of the data generating process when S is a random sample. Our main contribution is in proving that different statistical procedures can be strictly improved by applying different specific transformations to queries, and in providing explicit transformations for different procedures in some natural situations.

关键词： Gaussian mechanism Differential privacy Confidence region Testing hypotheses statistical inference on noisy data

来源：评论

学校读者我要写书评

暂无评论

On Integrating the Number of Synthetic Data Sets m into the a priori Synthesis Approach

On Integrating the Number of Synthetic Data Sets m into the ...

引用

international conference on privacy in statistical databases (psd)

作者： Jackson, James Mitra, Robin Francis, Brian Dove, Iain Univ Lancaster Lancaster England Cardiff Univ Cardiff Wales Off Natl Stat Titchfield England

ISBN: (纸本)9783031139451;9783031139444

The synthesis mechanism given in [4] uses saturated models, along with overdispersed count distributions, to generate synthetic categorical data. The mechanism is controlled by tuning parameters, which can be tuned according to a specific risk or utility metric. Thus expected properties of synthetic data sets can be determined analytically a priori, that is, before they are generated. While [4] considered the case of generating m = 1 data set, this paper considers generating m > 1 data sets. In effect, m becomes a tuning parameter and the role of m in relation to the risk-utility trade-off can be shown analytically. The paper introduces a pair of risk metrics, tau(3)(k, d) and tau(4)(k, d), that are suited to m > 1 data sets;and also considers the more general issue of how best to analyse m > 1 categorical data sets: average the data sets pre-analysis or average results post-analysis. Finally, the methods are demonstrated empirically with the synthesis of a constructed data set which is used to represent the English School Census.

关键词： Synthetic data privacy Categorical data Risk metrics Contingency tables

来源：评论

学校读者我要写书评

暂无评论

An Optimization-Based Decomposition Heuristic for the Microaggregation Problem

An Optimization-Based Decomposition Heuristic for the Microa...

引用

international conference on privacy in statistical databases (psd)

作者： Castro, Jordi Gentile, Claudio Spagnolo-Arrizabalaga, Enric Univ Politecn Cataluna Dept Stat & Operat Res Jordi Girona 1-3 Barcelona 08034 Spain CNR Ist Anal Sistemi Informat A Ruberti Rome Italy

ISBN: (纸本)9783031139451;9783031139444

Given a set of points, the microaggregation problem aims to find a clustering with a minimum sum of squared errors (SSE), where the cardinality of each cluster is greater than or equal to k. Points in the cluster are replaced by the cluster centroid, thus satisfying k-anonymity. Microaggregation is considered one of the most effective techniques for numerical microdata protection. Traditionally, non-optimal solutions to the microaggregation problem are obtained by heuristic approaches. Recently, the authors of this paper presented a mixed integer linear optimization (MILO) approach based on column generation for computing tight solutions and lower bounds to the microaggregation problem. However, MILO can be computationally expensive for large datasets. In this work we present a new heuristic that combines three blocks: (1) a decomposition of the dataset into subsets, (2) the MILO column generation algorithm applied to each dataset in order to obtain a valid microaggregation, and (3) a local search improvement algorithm to get the final clustering. Preliminary computational results show that this approach was able to provide (and even improve upon) some of the best solutions (i.e., of smallest SSE) reported in the literature for the Tarragona and Census datasets, and k is an element of{3, 5, 10}.

关键词： statistical disclosure control Microdata Microaggregation problem Mixed integer linear optimization Column generation Local search Heuristics

来源：评论

学校读者我要写书评

暂无评论

Membership Inference Attack Against Principal Component Analysis

Membership Inference Attack Against Principal Component Anal...

引用

international conference on privacy in statistical databases (psd)

作者： Zari, Oualid Parra-Arnau, Javier Unsal, Ayse Strufe, Thorsten Onen, Melek EURECOM Biot France Karlsruhe Inst Technol Karlsruhe Germany Univ Politecn Cataluna Barcelona Spain

ISBN: (纸本)9783031139451;9783031139444

This paper studies the performance of membership inference attacks against principal component analysis (PCA). In this attack, we assume that the adversary has access to the principal components, and her main goal is to infer whether a given data sample was used to compute these principal components. We show that our attack is successful and achieves high performance when the number of samples used to compute the principal components is small. As a defense strategy, we investigate the use of various differentially private mechanisms. Accordingly, we present experimental results on the performance of Gaussian and Laplace mechanisms under naive and advanced compositions against MIA as well as the utility of these differentially-private PCA solutions.

关键词： Membership inference attack Principal component analysis Differential privacy Laplace mechanism Gaussian mechanism

来源：评论

学校读者我要写书评

暂无评论

Tit-for-Tat Disclosure of a Binding Sequence of User Analyses in Safe Data Access Centers

Tit-for-Tat Disclosure of a Binding Sequence of User Analyse...

引用

international conference on privacy in statistical databases (psd)

作者： Domingo-Ferrer, Josep Univ Rovira & Virgili Dept Comp Engn & Math CYBERCAT Ctr Cybersecur Res Catalonia UNESCO Chair Data Privacy Av Paisos Catalans 26 Tarragona 43007 Spain

ISBN: (纸本)9783031139451;9783031139444

Safe access centers, a.k.a. trusted research environments, and digital marketplaces allow a user to submit her own statistical analyses on the data stored by controllers. As a responsible organization for the data, the controller may wish to enforce several ethical controls on the user's code. If data are personal or otherwise confidential, the controller needs to make sure the outputs of user analyses do not leak any personal information. Additionally, the data controller may require other ethical properties of the user analyses, like fairness or explainability in case an analysis consists of training a decision model. If a user analysis fails to meet the controller's ethical requirements, the controller stops running the user's code on his data. On the other side, the user would like to achieve fair disclosure of her code, that is, stop disclosing the remainder of her code to the controller in case the controller refuses to return the result of the current analysis. In this concept paper, we present a framework allowing the user: i) to bind herself to a sequence of analyses before receiving any actual output, which precludes disclosure attacks via adaptive analyses;ii) to disclose her next instruction/analysis to the controller only after the controller has returned the output of the current instruction/analysis, which ensures fair disclosure. Our aim is to protect both the controller's and the user's interests.

关键词： Safe access centers Digital marketplaces Trusted research environments Confidentiality Output checking Fairness Ethics

来源：评论

学校读者我要写书评

暂无评论

Quality Assessment of the 2014 to 2019 National Survey on Drug Use and Health (NSDUH) Public Use Files

Quality Assessment of the 2014 to 2019 National Survey on Dr...

引用

international conference on privacy in statistical databases (psd)

作者： Sathe, Neeraja Yu, Feng Dai, Lanting Cribb, Devon Spagnola, Kathryn Saravia, Ana Cai, Rong Hoenig, Jennifer RTI Int Res Triangle Pk NC 27709 USA Subst Abuse & Mental Hlth Serv Adm 5600 Fishers Lane Rockville MD 20857 USA

ISBN: (纸本)9783031139451;9783031139444

National Survey on Drug Use and Health (NSDUH) public use files (PUFs) have been produced using a statistical disclosure control technique named MASSC, which stands for Micro Agglomeration, Substitution, Subsampling, and Calibration, to protect confidentiality and quality of data. To inform researchers that NSDUH PUFs maintain high data quality and comparability with NSDUH restricted-use files (RUFs), about 300 NSDUH published tables (based on RUF data) of substance use and mental health were selected and reproduced using PUF data. Key estimates and their respective standard errors (SEs) produced from the two sets of 2014 to 2019 data files were compared. Summary statistics of ratios of the estimates and ratios of their SEs from PUF and RUF data were produced. Out of 22,000 estimates compared, average ratios for estimated percentages across years were within the 0.99 to 1.01 range, and the average increase in SEs for the estimates produced from PUFs across years was about 7-11%, for both substance use and mental health measures. Multiyear trend comparisons between PUF and RUF estimates were also conducted graphically to demonstrate PUF estimates provide similar trend patterns to RUF estimates across years. This study will provide confidence to researchers and policymakers for making policies and public health decisions based on NSDUH PUFs.

关键词： statistical disclosure limitation MASSC Quality assessment Public use file NSDUH

来源：评论

学校读者我要写书评

暂无评论

Automatic Evaluation of Disclosure Risks of Text Anonymization Methods

Automatic Evaluation of Disclosure Risks of Text Anonymizati...

引用

international conference on privacy in statistical databases (psd)

作者： Manzanares-Salor, Benet Sanchez, David Lison, Pierre Univ Rovira & Virgili Dept Comp Engn & Math UNESCO Chair Data Privacy CYBERCAT Tarragona Spain Norwegian Comp Ctr Oslo Norway

ISBN: (纸本)9783031139451;9783031139444

The standard approach to evaluate text anonymization methods consists of comparing their outcomes with the anonymization performed by human experts. The degree of privacy protection attained is then measured with the IR-based recall metric, which expresses the proportion of re-identifying terms that were correctly detected by the anonymization method. However, the use of recall to estimate the degree of privacy protection suffers from several limitations. The first is that it assigns a uniform weight to each re-identifying term, thereby ignoring the fact that some missed re-identifying terms may have a larger influence on the disclosure risk than others. Furthermore, IR-based metrics assume the existence of a single gold standard annotation. This assumption does not hold for text anonymization, where several maskings (each one encompassing a different combination of terms) could be equally valid to prevent disclosure. Finally, those metrics rely on manually anonymized datasets, which are inherently subjective and may be prone to various errors, omissions and inconsistencies. To tackle these issues, we propose an automatic re-identification attack for (anonymized) texts that provides a realistic assessment of disclosure risks. Our method follows a similar premise as the well-known record linkage methods employed to evaluate anonymized structured data, and leverages state-of-the-art deep learning language models to exploit the background knowledge available to potential attackers. We also report empirical evaluations of several well-known methods and tools for text anonymization. Results show significant re-identification risks for all methods, including also manual anonymization efforts.

关键词： Text anonymization Re-identification risk Language models BERT

来源：评论

学校读者我要写书评

暂无评论

Triggering Differential privacy to Counter Inference in statistical Database Security 2

Triggering Differential Privacy to Counter Inference in Stat...

引用

2nd international conference on Computing and Information Technology, ICCIT 2022

作者： Aljaedi, Amer College of Computing and Information Technology University of Tabuk Tabuk71491 Saudi Arabia

ISBN: (纸本)9781665436052

Inference attacks on statistical databases represent a complex issue in institutions and corporates since it is hard to detect and prevent, especially when it is committed by an internal adversary. The issue has been manifested further with the widespread of data analytics techniques in industry and academia, besides outsourced services. Even when the released statistical data has been anonymized and the identifying attributes are removed, targeted individuals can be spotted in such data. Therefore, preventing sensitive statistical data leakage is crucial for protecting the privacy of individuals or events, but such measures should not form utilization obstacles or degrade the data utility. This paper proposes an anti-inference technique for preserving the privacy of sensitive data in statistical databases. Unlike existing solutions, which either require considerable computing resources or trade-off between statistical data accuracy and its privacy, our solution is designed to maintain the accuracy while privacy is ensured. © 2022 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共13页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：