PrivKVM: Revisiting Key-Value Statistics Estimation With Local Differential Privacy
A key factor in big data analytics and artificial intelligence is the collection of user data from a large population. However, the collection of user data comes at the price of privacy risks, not only for users but also for businesses who are vulnerable to internal and external data breaches. To ad...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on dependable and secure computing 2023-01, Vol.20 (1), p.17-35 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 35 |
|---|---|
| container_issue | 1 |
| container_start_page | 17 |
| container_title | IEEE transactions on dependable and secure computing |
| container_volume | 20 |
| creator | Ye, Qingqing Hu, Haibo Meng, Xiaofeng Zheng, Huadi Huang, Kai Fang, Chengfang Shi, Jie |
| description | A key factor in big data analytics and artificial intelligence is the collection of user data from a large population. However, the collection of user data comes at the price of privacy risks, not only for users but also for businesses who are vulnerable to internal and external data breaches. To address privacy issues, local differential privacy (LDP) has been proposed to enable an untrusted collector to obtain accurate statistical estimation on sensitive user data (e.g., location, health, and financial data) without actually accessing the true records. As key-value data is an extremely popular NoSQL data model, there are a few works in the literature that study LDP-based statistical estimation on key-value data. However, these works have some major limitations, including supporting small key space only, fixed key collection range, difficulty in choosing an appropriate padding length, and high communication cost. In this article, we propose a two-phase mechanism PrivKVM^* PrivKVM* as an optimized and highly-complete solution to LDP-based key-value data collection and statistics estimation. We verify its correctness and effectiveness through rigorous theoretical analysis and extensive experimental results. |
| doi_str_mv | 10.1109/TDSC.2021.3107512 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2765185879</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9524509</ieee_id><sourcerecordid>2765185879</sourcerecordid><originalsourceid>FETCH-LOGICAL-c336t-31cf75efb1a3945ffa274e5b6cc2b5ac024174b15c7dbc26f66264381ec672473</originalsourceid><addsrcrecordid>eNo9UE1PAjEU3BhNRPQHGC-beF7s6-fWmwH8CBiNIB6bbm21BHdxW0j493YD8TRvkpl5702WXQIaACB5Mx_NhgOMMAwIIMEAH2U9kBQKhKA8TjOjrGBSwGl2FsISIUxLSXvZ7LX128ni-TZ_s1sffPT1Vz6xu2KhVxubz6KOPkRvQj5O8JNYU-cfPn7n08boVT7yztnW1tEn0mVpszvPTpxeBXtxwH72fj-eDx-L6cvD0_BuWhhCeCwIGCeYdRVoIilzTmNBLau4Mbhi2qQTQdAKmBGflcHccY45JSVYwwWmgvSz633uum1-NzZEtWw2bZ1WKiw4g5KVQiYV7FWmbUJorVPrNj3S7hQg1XWnuu5U1506dJc8V3uPt9b-6yXDlCFJ_gBPyWo5</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2765185879</pqid></control><display><type>article</type><title>PrivKVM: Revisiting Key-Value Statistics Estimation With Local Differential Privacy</title><source>IEEE Electronic Library (IEL)</source><creator>Ye, Qingqing ; Hu, Haibo ; Meng, Xiaofeng ; Zheng, Huadi ; Huang, Kai ; Fang, Chengfang ; Shi, Jie</creator><creatorcontrib>Ye, Qingqing ; Hu, Haibo ; Meng, Xiaofeng ; Zheng, Huadi ; Huang, Kai ; Fang, Chengfang ; Shi, Jie</creatorcontrib><description><![CDATA[A key factor in big data analytics and artificial intelligence is the collection of user data from a large population. However, the collection of user data comes at the price of privacy risks, not only for users but also for businesses who are vulnerable to internal and external data breaches. To address privacy issues, local differential privacy (LDP) has been proposed to enable an untrusted collector to obtain accurate statistical estimation on sensitive user data (e.g., location, health, and financial data) without actually accessing the true records. As key-value data is an extremely popular NoSQL data model, there are a few works in the literature that study LDP-based statistical estimation on key-value data. However, these works have some major limitations, including supporting small key space only, fixed key collection range, difficulty in choosing an appropriate padding length, and high communication cost. In this article, we propose a two-phase mechanism <inline-formula><tex-math notation="LaTeX">PrivKVM^*</tex-math> <mml:math><mml:mrow><mml:mi>P</mml:mi><mml:mi>r</mml:mi><mml:mi>i</mml:mi><mml:mi>v</mml:mi><mml:mi>K</mml:mi><mml:mi>V</mml:mi><mml:msup><mml:mi>M</mml:mi><mml:mo>*</mml:mo></mml:msup></mml:mrow></mml:math><inline-graphic xlink:href="ye-ieq1-3107512.gif"/> </inline-formula> as an optimized and highly-complete solution to LDP-based key-value data collection and statistics estimation. We verify its correctness and effectiveness through rigorous theoretical analysis and extensive experimental results.]]></description><identifier>ISSN: 1545-5971</identifier><identifier>EISSN: 1941-0018</identifier><identifier>DOI: 10.1109/TDSC.2021.3107512</identifier><identifier>CODEN: ITDSCM</identifier><language>eng</language><publisher>Washington: IEEE</publisher><subject>Artificial intelligence ; Big Data ; Data collection ; Differential privacy ; Estimation ; Extreme values ; Frequency estimation ; histogram ; Histograms ; Key-value data ; local differential privacy ; Perturbation methods ; Privacy ; privacy-preserving data collection ; statistics estimation</subject><ispartof>IEEE transactions on dependable and secure computing, 2023-01, Vol.20 (1), p.17-35</ispartof><rights>Copyright IEEE Computer Society 2023</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c336t-31cf75efb1a3945ffa274e5b6cc2b5ac024174b15c7dbc26f66264381ec672473</citedby><cites>FETCH-LOGICAL-c336t-31cf75efb1a3945ffa274e5b6cc2b5ac024174b15c7dbc26f66264381ec672473</cites><orcidid>0000-0003-1547-2847 ; 0000-0001-9857-654X ; 0000-0003-1224-9885 ; 0000-0002-9008-2112</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9524509$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,777,781,793,27905,27906,54739</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9524509$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ye, Qingqing</creatorcontrib><creatorcontrib>Hu, Haibo</creatorcontrib><creatorcontrib>Meng, Xiaofeng</creatorcontrib><creatorcontrib>Zheng, Huadi</creatorcontrib><creatorcontrib>Huang, Kai</creatorcontrib><creatorcontrib>Fang, Chengfang</creatorcontrib><creatorcontrib>Shi, Jie</creatorcontrib><title>PrivKVM: Revisiting Key-Value Statistics Estimation With Local Differential Privacy</title><title>IEEE transactions on dependable and secure computing</title><addtitle>TDSC</addtitle><description><![CDATA[A key factor in big data analytics and artificial intelligence is the collection of user data from a large population. However, the collection of user data comes at the price of privacy risks, not only for users but also for businesses who are vulnerable to internal and external data breaches. To address privacy issues, local differential privacy (LDP) has been proposed to enable an untrusted collector to obtain accurate statistical estimation on sensitive user data (e.g., location, health, and financial data) without actually accessing the true records. As key-value data is an extremely popular NoSQL data model, there are a few works in the literature that study LDP-based statistical estimation on key-value data. However, these works have some major limitations, including supporting small key space only, fixed key collection range, difficulty in choosing an appropriate padding length, and high communication cost. In this article, we propose a two-phase mechanism <inline-formula><tex-math notation="LaTeX">PrivKVM^*</tex-math> <mml:math><mml:mrow><mml:mi>P</mml:mi><mml:mi>r</mml:mi><mml:mi>i</mml:mi><mml:mi>v</mml:mi><mml:mi>K</mml:mi><mml:mi>V</mml:mi><mml:msup><mml:mi>M</mml:mi><mml:mo>*</mml:mo></mml:msup></mml:mrow></mml:math><inline-graphic xlink:href="ye-ieq1-3107512.gif"/> </inline-formula> as an optimized and highly-complete solution to LDP-based key-value data collection and statistics estimation. We verify its correctness and effectiveness through rigorous theoretical analysis and extensive experimental results.]]></description><subject>Artificial intelligence</subject><subject>Big Data</subject><subject>Data collection</subject><subject>Differential privacy</subject><subject>Estimation</subject><subject>Extreme values</subject><subject>Frequency estimation</subject><subject>histogram</subject><subject>Histograms</subject><subject>Key-value data</subject><subject>local differential privacy</subject><subject>Perturbation methods</subject><subject>Privacy</subject><subject>privacy-preserving data collection</subject><subject>statistics estimation</subject><issn>1545-5971</issn><issn>1941-0018</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9UE1PAjEU3BhNRPQHGC-beF7s6-fWmwH8CBiNIB6bbm21BHdxW0j493YD8TRvkpl5702WXQIaACB5Mx_NhgOMMAwIIMEAH2U9kBQKhKA8TjOjrGBSwGl2FsISIUxLSXvZ7LX128ni-TZ_s1sffPT1Vz6xu2KhVxubz6KOPkRvQj5O8JNYU-cfPn7n08boVT7yztnW1tEn0mVpszvPTpxeBXtxwH72fj-eDx-L6cvD0_BuWhhCeCwIGCeYdRVoIilzTmNBLau4Mbhi2qQTQdAKmBGflcHccY45JSVYwwWmgvSz633uum1-NzZEtWw2bZ1WKiw4g5KVQiYV7FWmbUJorVPrNj3S7hQg1XWnuu5U1506dJc8V3uPt9b-6yXDlCFJ_gBPyWo5</recordid><startdate>202301</startdate><enddate>202301</enddate><creator>Ye, Qingqing</creator><creator>Hu, Haibo</creator><creator>Meng, Xiaofeng</creator><creator>Zheng, Huadi</creator><creator>Huang, Kai</creator><creator>Fang, Chengfang</creator><creator>Shi, Jie</creator><general>IEEE</general><general>IEEE Computer Society</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>JQ2</scope><orcidid>https://orcid.org/0000-0003-1547-2847</orcidid><orcidid>https://orcid.org/0000-0001-9857-654X</orcidid><orcidid>https://orcid.org/0000-0003-1224-9885</orcidid><orcidid>https://orcid.org/0000-0002-9008-2112</orcidid></search><sort><creationdate>202301</creationdate><title>PrivKVM: Revisiting Key-Value Statistics Estimation With Local Differential Privacy</title><author>Ye, Qingqing ; Hu, Haibo ; Meng, Xiaofeng ; Zheng, Huadi ; Huang, Kai ; Fang, Chengfang ; Shi, Jie</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c336t-31cf75efb1a3945ffa274e5b6cc2b5ac024174b15c7dbc26f66264381ec672473</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial intelligence</topic><topic>Big Data</topic><topic>Data collection</topic><topic>Differential privacy</topic><topic>Estimation</topic><topic>Extreme values</topic><topic>Frequency estimation</topic><topic>histogram</topic><topic>Histograms</topic><topic>Key-value data</topic><topic>local differential privacy</topic><topic>Perturbation methods</topic><topic>Privacy</topic><topic>privacy-preserving data collection</topic><topic>statistics estimation</topic><toplevel>online_resources</toplevel><creatorcontrib>Ye, Qingqing</creatorcontrib><creatorcontrib>Hu, Haibo</creatorcontrib><creatorcontrib>Meng, Xiaofeng</creatorcontrib><creatorcontrib>Zheng, Huadi</creatorcontrib><creatorcontrib>Huang, Kai</creatorcontrib><creatorcontrib>Fang, Chengfang</creatorcontrib><creatorcontrib>Shi, Jie</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>ProQuest Computer Science Collection</collection><jtitle>IEEE transactions on dependable and secure computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ye, Qingqing</au><au>Hu, Haibo</au><au>Meng, Xiaofeng</au><au>Zheng, Huadi</au><au>Huang, Kai</au><au>Fang, Chengfang</au><au>Shi, Jie</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>PrivKVM: Revisiting Key-Value Statistics Estimation With Local Differential Privacy</atitle><jtitle>IEEE transactions on dependable and secure computing</jtitle><stitle>TDSC</stitle><date>2023-01</date><risdate>2023</risdate><volume>20</volume><issue>1</issue><spage>17</spage><epage>35</epage><pages>17-35</pages><issn>1545-5971</issn><eissn>1941-0018</eissn><coden>ITDSCM</coden><abstract><![CDATA[A key factor in big data analytics and artificial intelligence is the collection of user data from a large population. However, the collection of user data comes at the price of privacy risks, not only for users but also for businesses who are vulnerable to internal and external data breaches. To address privacy issues, local differential privacy (LDP) has been proposed to enable an untrusted collector to obtain accurate statistical estimation on sensitive user data (e.g., location, health, and financial data) without actually accessing the true records. As key-value data is an extremely popular NoSQL data model, there are a few works in the literature that study LDP-based statistical estimation on key-value data. However, these works have some major limitations, including supporting small key space only, fixed key collection range, difficulty in choosing an appropriate padding length, and high communication cost. In this article, we propose a two-phase mechanism <inline-formula><tex-math notation="LaTeX">PrivKVM^*</tex-math> <mml:math><mml:mrow><mml:mi>P</mml:mi><mml:mi>r</mml:mi><mml:mi>i</mml:mi><mml:mi>v</mml:mi><mml:mi>K</mml:mi><mml:mi>V</mml:mi><mml:msup><mml:mi>M</mml:mi><mml:mo>*</mml:mo></mml:msup></mml:mrow></mml:math><inline-graphic xlink:href="ye-ieq1-3107512.gif"/> </inline-formula> as an optimized and highly-complete solution to LDP-based key-value data collection and statistics estimation. We verify its correctness and effectiveness through rigorous theoretical analysis and extensive experimental results.]]></abstract><cop>Washington</cop><pub>IEEE</pub><doi>10.1109/TDSC.2021.3107512</doi><tpages>19</tpages><orcidid>https://orcid.org/0000-0003-1547-2847</orcidid><orcidid>https://orcid.org/0000-0001-9857-654X</orcidid><orcidid>https://orcid.org/0000-0003-1224-9885</orcidid><orcidid>https://orcid.org/0000-0002-9008-2112</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1545-5971 |
| ispartof | IEEE transactions on dependable and secure computing, 2023-01, Vol.20 (1), p.17-35 |
| issn | 1545-5971 1941-0018 |
| language | eng |
| recordid | cdi_proquest_journals_2765185879 |
| source | IEEE Electronic Library (IEL) |
| subjects | Artificial intelligence Big Data Data collection Differential privacy Estimation Extreme values Frequency estimation histogram Histograms Key-value data local differential privacy Perturbation methods Privacy privacy-preserving data collection statistics estimation |
| title | PrivKVM: Revisiting Key-Value Statistics Estimation With Local Differential Privacy |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T20%3A51%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=PrivKVM:%20Revisiting%20Key-Value%20Statistics%20Estimation%20With%20Local%20Differential%20Privacy&rft.jtitle=IEEE%20transactions%20on%20dependable%20and%20secure%20computing&rft.au=Ye,%20Qingqing&rft.date=2023-01&rft.volume=20&rft.issue=1&rft.spage=17&rft.epage=35&rft.pages=17-35&rft.issn=1545-5971&rft.eissn=1941-0018&rft.coden=ITDSCM&rft_id=info:doi/10.1109/TDSC.2021.3107512&rft_dat=%3Cproquest_RIE%3E2765185879%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2765185879&rft_id=info:pmid/&rft_ieee_id=9524509&rfr_iscdi=true |