Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
    • 指導教授
  • 搜尋 TDR
  • 授權 Q&A
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 電機資訊學院
  3. 資訊網路與多媒體研究所
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/73920
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor蕭旭君(Hsu-Chun Hsiao)
dc.contributor.authorTing-Wei Laien
dc.contributor.author賴廷威zh_TW
dc.date.accessioned2021-06-17T08:13:47Z-
dc.date.available2019-08-20
dc.date.copyright2019-08-20
dc.date.issued2019
dc.date.submitted2019-08-14
dc.identifier.citation[1] https://money.cnn.com/galleries/2010/technology/1012/gallery.5_data_ breaches/index.html.
[2] Daily air quality index. https://uk-air.defra.gov.uk/air-pollution/daqi.
[3] Qp solvers. https://pypi.org/project/qpsolvers/.
[4] Scistarter. https://scistarter.org/events.
[5] Taiwan air quality monitoring network.
[6] Apple. Learning with privacy at scale. 2017.
[7] B. Ding, J. Kulkarni, and S. Yekhanin. Collecting telemetry data privately. In Ad- vances in Neural Information Processing Systems, pages 3571–3580, 2017.
[8] C. Dwork. Differential privacy. In 33rd International Colloquium on Automata, Languages and Programming, part II (ICALP 2006), volume 4052 of Lecture Notes in Computer Science, pages 1–12. Springer Verlag, July 2006.
[9] C. Dwork, M. Naor, O. Reingold, G.N. Rothblum, and S. Vadhan. Onthecomplexity of differentially private data release: efficient algorithms and hardness results. In Proceedings of the forty-first annual ACM symposium on Theory of computing, pages 381–390. ACM, 2009.
[10] C. Dwork and G. N. Rothblum. Concentrated differential privacy. arXiv preprint arXiv:1603.01887, 2016.
[11] Ú. Erlingsson, V. Pihur, and A. Korolova. Rappor: Randomized aggregatable privacy-preserving ordinal response. In Proceedings of the 2014 ACM SIGSAC con- ference on computer and communications security, pages 1054–1067. ACM, 2014.
[12] M.Hay, V.Rastogi, G.Miklau, and D.Suciu. Boosting the accuracy of differentially private histograms through consistency. Proceedings of the VLDB Endowment, 3(1- 2):1021–1032, 2010.
[13] Y.-H. Kuo, C.-C. Chiu, D. Kifer, M. Hay, and A. Machanavajjhala. Differentially private hierarchical count-of-counts histograms. Proceedings of the VLDB Endow- ment, 11(11):1509–1521, 2018.
[14] T. Wang, N. Li, and S. Jha. Locally differentially private frequent itemset mining. In 2018 IEEE Symposium on Security and Privacy (SP), pages 127–143. IEEE, 2018.
[15] T. Wang, Z. Li, N. Li, M. Lopuhaä-Zwakenberg, and B. Skoric. Consistent and accurate frequency oracles under local differential privacy. arXiv preprint arXiv:1905.08320, 2019.
[16] S. L. Warner. Randomized response: A survey technique for eliminating evasive answer bias. Journal of the American Statistical Association, 60(309):63–69, 1965.
[17] Z. Zhang, T. Wang, N. Li, S. He, and J. Chen. Calm: Consistent adaptive local marginal for marginal release under local differential privacy. In Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, pages 212–229. ACM, 2018.
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/73920-
dc.description.abstract我們考慮以下的一類資料查詢問題,我們稱呼這種問題為分層資料 計數問題。在分層資料計數問題中,資料提供者會根據他們手中的資 料進行分組,例如以資料提供者的所在位置的區域作為分組方式。資 料提供者希望能在隱密並且本地進行的環境下回報他們的資料。對分 層資料計數問題進行查詢可以得到所有資料提供者在各個預先定義好 的階層架構中的數量,例如在全國、各大區、各縣中資料提供者的數 量。在這篇論文中,我們提出了分層資料計數問題並且提出了一個基 於分散式架構中的差分隱私演算法並且使得分層資料計數問題的結果 是在各個分層中都是一致的。在我們的實驗中,我們提出的演算法相 較於無一致性的本地差分隱私演算法可以有效地減少雜訊量並且對於 顯著類別的估計有較好的預測。zh_TW
dc.description.abstractWe consider the problem of privately and distributedly conducting a class of queries that we call hierarchical data counting. Hierarchical data count- ing partition users into groups (e.g., grouping people who locate in the same area) by the values that users own, and each user may report his value and groups in private and local settings. Hierarchical data counting queries can report the count of user values at different granularities according to a pre- defined hierarchy (e.g., geographical location of the user at the national, state, and county levels). In this paper, we introduce this problem and propose a local differential private solution that generates hierarchical data counting histograms that are consistent across all levels of the hierarchy. In our exper- iment, our solution can greatly decrease the amount of noise and give a more precise heavy-hitter estimation comparing to the local differential privacy al- gorithm without consistency.en
dc.description.provenanceMade available in DSpace on 2021-06-17T08:13:47Z (GMT). No. of bitstreams: 1
ntu-108-R06944011-1.pdf: 2893140 bytes, checksum: 0e242e094b11a22cd0374e65279c7634 (MD5)
Previous issue date: 2019
en
dc.description.tableofcontents口試委員會審定書 i
誌謝 ii
Acknowledgements iii
摘要 iv
Abstract v
1 Introduction 1
2 Background 4
2.1 Differential Privacy............................. 4
2.2 Local Differential Privacy ......................... 5
2.3 Hierarchical Data Counting......................... 7
2.3.1 Consistency Constraint....................... 8
3 Problem Definition 10
3.1 Local differential Privacy with Hierarchy . . . . . . . . . . . . . . . . . 10
3.2 Attacker Model ............................... 11
4 Proposed Solution 12
4.1 Challenge.................................. 12
4.2 User Side Algorithm ............................ 13
4.3 Aggregator Side Algorithm......................... 14
4.3.1 Consistency Update Algorithm................... 15
5 Evaluation 17
5.1 Experimental Setup............................. 17
5.2 Average Noise................................ 18
5.3 Top K.................................... 18
5.4 Performance Evaluation........................... 22
6 Related Work 23
7 Conclusion 25
Bibliography 26
dc.language.isoen
dc.subject本地差分隱私zh_TW
dc.subject差分隱私zh_TW
dc.subject隱私zh_TW
dc.subject資料計數zh_TW
dc.subjectDifferential Privacyen
dc.subjectLocal Differential Privacyen
dc.subjectPrivacyen
dc.subjectData Countingen
dc.title在分散式環境中實現差分隱私與一致性的分層資料計數zh_TW
dc.titleDifferentially private and consistent hierarchical data counting in distributed settingsen
dc.typeThesis
dc.date.schoolyear107-2
dc.description.degree碩士
dc.contributor.oralexamcommittee吳家麟(Ja-Ling Wu),林忠緯(Chung-Wei Lin),游家牧(Chia-Mu Yu)
dc.subject.keyword差分隱私,本地差分隱私,隱私,資料計數,zh_TW
dc.subject.keywordDifferential Privacy,Local Differential Privacy,Privacy,Data Counting,en
dc.relation.page27
dc.identifier.doi10.6342/NTU201903680
dc.rights.note有償授權
dc.date.accepted2019-08-15
dc.contributor.author-college電機資訊學院zh_TW
dc.contributor.author-dept資訊網路與多媒體研究所zh_TW
顯示於系所單位:資訊網路與多媒體研究所

文件中的檔案:
檔案 大小格式 
ntu-108-1.pdf
  未授權公開取用
2.83 MBAdobe PDF
顯示文件簡單紀錄


系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved