國立虎尾科技大學 |

Privacy or Utility? How to Preserve Both in Outlier Analysis.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Privacy or Utility? How to Preserve Both in Outlier Analysis./
作者:	Asif, Hafiz Salman.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	151 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-12, Section: B.
Contained By:	Dissertations Abstracts International82-12B.
標題:	Information science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28264552
ISBN:	9798597096100

Privacy or Utility? How to Preserve Both in Outlier Analysis.
Asif, Hafiz Salman.

Privacy or Utility? How to Preserve Both in Outlier Analysis. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 151 p.

Source: Dissertations Abstracts International, Volume: 82-12, Section: B.

Thesis (Ph.D.)--Rutgers The State University of New Jersey, Graduate School - Newark, 2021.

This item must not be sold to any third party vendors.

Data analysts use outlier analysis to discover non-conforming patterns in data to generate actionable insights. It is an incredibly useful approach, but like all data-driven approaches, it raises privacy-related serious ethical and legal concerns when data is about peoples’ information. Is it possible to accurately analyze data for outliers while protecting the privacy of people whose data we analyze? In this dissertation, we explicate methods to answer this question for the most practically relevant case, where outliers are defined in a data-dependent way and current privacy methods such as differential privacy fail to achieve practically meaningful utility.To define what it means to protect privacy in outlier analysis, we conceptualize sensitive privacy — it not only admits eﬀicient algorithmic constructions but is also amenable to analysis. We introduce novel constructions to develop sensitively private mechanisms to accurately identify outliers, and to compile low-accuracy differentially private mechanisms into high-accuracy sensitively private mechanisms. Furthermore, to address the lack of a principled approach to private outlier analysis, we provide a framework to help a data analyst identify the right problem-specification and a practical solution for her application.Finally, we develop mechanisms — which guarantee privacy and practically meaningful utility — to identify (β,r)-anomalies as well as covid-19 hotspots (an outlying event). An extensive empirical evaluation of these private mechanisms over a range of real-world datasets and use cases overwhelmingly supports the effectiveness of our approach.

ISBN: 9798597096100Subjects--Topical Terms:

561178
Information science.
Subjects--Index Terms:

Differential privacy

Privacy or Utility? How to Preserve Both in Outlier Analysis.
LDR:02859nam a2200385 4500 001 1067156
005 20220823142303.5
008 221020s2021 ||||||||||||||||| ||eng d
020 $a 9798597096100
035 $a (MiAaPQ)AAI28264552
035 $a AAI28264552
040 $a MiAaPQ $c MiAaPQ
100 1 $a Asif, Hafiz Salman. $3 1372507
245 1 0 $a Privacy or Utility? How to Preserve Both in Outlier Analysis.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 151 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-12, Section: B.
500 $a Advisor: Vaidya, Jaideep.
502 $a Thesis (Ph.D.)--Rutgers The State University of New Jersey, Graduate School - Newark, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Data analysts use outlier analysis to discover non-conforming patterns in data to generate actionable insights. It is an incredibly useful approach, but like all data-driven approaches, it raises privacy-related serious ethical and legal concerns when data is about peoples’ information. Is it possible to accurately analyze data for outliers while protecting the privacy of people whose data we analyze? In this dissertation, we explicate methods to answer this question for the most practically relevant case, where outliers are defined in a data-dependent way and current privacy methods such as differential privacy fail to achieve practically meaningful utility.To define what it means to protect privacy in outlier analysis, we conceptualize sensitive privacy — it not only admits eﬀicient algorithmic constructions but is also amenable to analysis. We introduce novel constructions to develop sensitively private mechanisms to accurately identify outliers, and to compile low-accuracy differentially private mechanisms into high-accuracy sensitively private mechanisms. Furthermore, to address the lack of a principled approach to private outlier analysis, we provide a framework to help a data analyst identify the right problem-specification and a practical solution for her application.Finally, we develop mechanisms — which guarantee privacy and practically meaningful utility — to identify (β,r)-anomalies as well as covid-19 hotspots (an outlying event). An extensive empirical evaluation of these private mechanisms over a range of real-world datasets and use cases overwhelmingly supports the effectiveness of our approach.
590 $a School code: 0461.
650 4 $a Information science. $3 561178
650 4 $a Information technology. $3 559429
650 4 $a Computer science. $3 573171
653 $a Differential privacy
653 $a Outlier detection
653 $a Privacy
653 $a Privacy preserving
653 $a Data analysis
690 $a 0984
690 $a 0489
690 $a 0454
690 $a 0723
710 2 $a Rutgers The State University of New Jersey, Graduate School - Newark. $b Mathematical Sciences. $3 1372508
773 0 $t Dissertations Abstracts International $g 82-12B.
790 $a 0461
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28264552