서브메뉴
검색
상세정보
Bridging Sociotechnical Gaps for Privacy-Preserving Data Science- [electronic resource]
![Bridging Sociotechnical Gaps for Privacy-Preserving Data Science - [electronic resource] /...](/Sponge/Images/bookDefaults/DDbookdefaultsmall.png)
Bridging Sociotechnical Gaps for Privacy-Preserving Data Science- [electronic resource]
상세정보
- 자료유형
- 학위논문(국외)
- 자관 청구기호
- 기본표목-개인명
- 표제와 책임표시사항
- Bridging Sociotechnical Gaps for Privacy-Preserving Data Science - [electronic resource] / Jayshree Sarathy
- 발행, 배포, 간사 사항
- 발행, 배포, 간사 사항
- 형태사항
- 1 online resource(p.292 )
- 일반주기
- Source: Dissertations Abstracts International, Volume: 84-12, Section: A.
- 일반주기
- Advisor: Vadhan, Salil;Zittrain, Jonathan.
- 학위논문주기
- Thesis (Ph.D.)--Harvard University, 2023.
- 이용제한주기
- This item must not be sold to any third party vendors.
- 요약 등 주기
- 요약Over the last two decades, a rapid rise in computational power, availability of data sources, and data-based systems has created new threats for the privacy of data subjects. This dissertation considers differential privacy (DP), a mathematical framework for guaranteeing that an algorithm reveals little about any individual data record, even to an attacker with additional information about the dataset. DP has a rich theoretical literature, but there have been many challenges when integrating the theory of DP with the practices of data science. In addition, recent deployments of DP across government and industry have highlighted the complexities around communicating the goals and guarantees of DP to stakeholders.This dissertation combines perspectives from Computer Science and Science & Technology Studies to offer new ways of understanding and addressing the challenges around practical, privacy-preserving data science. In particular, this thesis analyzes the tensions between theory and practice along empirical, mathematical, and sociotechnical dimensions. The contributions of this thesis include (1) empirically investigating the utility of differential privacy for social science researchers, highlighting several social and conceptual barriers to adoption, (2) designing and analyzing differentially private algorithms for fundamental, yet under-studied statistical tasks within the constraints of differential privacy, such as simple linear regression, and (3) exploring the entanglements between differential privacy as a mathematical formalization and its socio-political impacts in real-world settings. The dissertation concludes with suggestions for further technical and critical inquiry into the impacts of differential privacy in practice.
- 주제명부출표목-일반주제명
- 주제명부출표목-일반주제명
- 주제명부출표목-일반주제명
- 비통제 색인어
- 비통제 색인어
- 비통제 색인어
- 비통제 색인어
- 비통제 색인어
- 부출표목-단체명
- 기본자료저록
- Dissertations Abstracts International. 84-12A.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 원문정보보기
- 소장사항
-
202402 2024
MARC
008240306s2023 us s 000c| eng d■001000016932311
■00520240214100441
■006m o d
■007cr
■020 ▼a9798379603595
■035 ▼a(MiAaPQ)AAI30491364
■040 ▼aMiAaPQ▼cMiAaPQ
■08204▼a004▼222
■090 ▼a전자도서(박사논문)
■1001 ▼aSarathy, Jayshree.▼0(orcid)0000-0001-5852-5182
■24510▼aBridging Sociotechnical Gaps for Privacy-Preserving Data Science▼h[electronic resource]▼cJayshree Sarathy
■260 ▼a[S.l.]▼bHarvard University. ▼c2023
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2023
■300 ▼a1 online resource(p.292 )
■500 ▼aSource: Dissertations Abstracts International, Volume: 84-12, Section: A.
■500 ▼aAdvisor: Vadhan, Salil;Zittrain, Jonathan.
■5021 ▼aThesis (Ph.D.)--Harvard University, 2023.
■506 ▼aThis item must not be sold to any third party vendors.
■520 ▼aOver the last two decades, a rapid rise in computational power, availability of data sources, and data-based systems has created new threats for the privacy of data subjects. This dissertation considers differential privacy (DP), a mathematical framework for guaranteeing that an algorithm reveals little about any individual data record, even to an attacker with additional information about the dataset. DP has a rich theoretical literature, but there have been many challenges when integrating the theory of DP with the practices of data science. In addition, recent deployments of DP across government and industry have highlighted the complexities around communicating the goals and guarantees of DP to stakeholders.This dissertation combines perspectives from Computer Science and Science & Technology Studies to offer new ways of understanding and addressing the challenges around practical, privacy-preserving data science. In particular, this thesis analyzes the tensions between theory and practice along empirical, mathematical, and sociotechnical dimensions. The contributions of this thesis include (1) empirically investigating the utility of differential privacy for social science researchers, highlighting several social and conceptual barriers to adoption, (2) designing and analyzing differentially private algorithms for fundamental, yet under-studied statistical tasks within the constraints of differential privacy, such as simple linear regression, and (3) exploring the entanglements between differential privacy as a mathematical formalization and its socio-political impacts in real-world settings. The dissertation concludes with suggestions for further technical and critical inquiry into the impacts of differential privacy in practice.
■590 ▼aSchool code: 0084.
■650 4▼aComputer science.
■650 4▼aComputer engineering.
■650 4▼aInformation science.
■653 ▼aData science
■653 ▼aDifferential privacy
■653 ▼aLinear regression
■653 ▼aSociotechnical systems
■653 ▼aSocio-political impacts
■690 ▼a0984
■690 ▼a0464
■690 ▼a0723
■71020▼aHarvard University▼bEngineering and Applied Sciences - Computer Science.
■7730 ▼tDissertations Abstracts International▼g84-12A.
■773 ▼tDissertation Abstract International
■790 ▼a0084
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16932311▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
■980 ▼a202402▼f2024
한글
ENG
日本
中文
Việt Nam