HEaaN-NB: Non-Interactive Privacy-Preserving Naive Bayes Using CKKS for Secure Outsourced Cloud Computing
Although there has been significant progress in homomorphic encryption (HE) technology, a fully homomorphic Naive Bayes (NB) classifier capable of training on HE-encrypted data without decryption has not yet been efficiently developed. This research introduces a new method for approximating homomorp...
Gespeichert in:
| Veröffentlicht in: | IEEE access 2024, Vol.12, p.110762-110780 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 110780 |
|---|---|
| container_issue | |
| container_start_page | 110762 |
| container_title | IEEE access |
| container_volume | 12 |
| creator | Han, Boyoung Shin, Hojune Kim, Yeonghyeon Choi, Jina Lee, Younho |
| description | Although there has been significant progress in homomorphic encryption (HE) technology, a fully homomorphic Naive Bayes (NB) classifier capable of training on HE-encrypted data without decryption has not yet been efficiently developed. This research introduces a new method for approximating homomorphic logarithm calculations with an average relative error under 0.01%. Leveraging the SIMD functionality of the HE framework and a GPU, this technique can compute logarithm values for thousands of encrypted probabilities in about 2.5 seconds. Building upon this, we present a more efficient fully homomorphic NB classifier. Our method can train on a breast cancer dataset in roughly 14.3 seconds and perform query inferences in 0.84 seconds. Compared to the recent privacy-protecting NB classifier from Liu et al. in 2017, which offers a similar security level, our method is estimated to be about 28 times faster. |
| doi_str_mv | 10.1109/ACCESS.2024.3438161 |
| format | Article |
| fullrecord | <record><control><sourceid>doaj_ieee_</sourceid><recordid>TN_cdi_ieee_primary_10623150</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10623150</ieee_id><doaj_id>oai_doaj_org_article_6b345d253bf7452996dc01860e4fefff</doaj_id><sourcerecordid>oai_doaj_org_article_6b345d253bf7452996dc01860e4fefff</sourcerecordid><originalsourceid>FETCH-LOGICAL-c261t-6a96ada41e1adb3354206a23fbfb8a65370b34cf7758ad5782a5ddfa679a7dcd3</originalsourceid><addsrcrecordid>eNpNkN1Kw0AQhYMoWNQn0Iu8QOr-ZDeJdzVUW5S0EL1eJruzEmm7ZTcp9O1NbBHnYmY4M-e7OFF0T8mUUlI8zspyXtdTRlg65SnPqaQX0YRRWSRccHn5b7-O7kL4JkMNX4XIJlG7mANUSfX8FFdulyx3HXrQXXvAeO3bA-hjsvYY0B_a3VdcwXh4hiOG-DOMSvn2VsfW-bhG3XuMV30XXO81mrjcuH7obrvvu-H1NrqysAl4d5430efL_KNcJO-r12U5e080k7RLJBQSDKQUKZiGc5EyIoFx29gmByl4RhqeaptlIgcjspyBMMaCzArIjDb8JlqeuMbBt9r7dgv-qBy06ldw_kuB71q9QSUHkjBM8MZmqWBFIY0mNJcEU4vW2oHFTyztXQge7R-PEjWGr07hqzF8dQ5_cD2cXC0i_nNIxqkg_Ae7TYDh</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>HEaaN-NB: Non-Interactive Privacy-Preserving Naive Bayes Using CKKS for Secure Outsourced Cloud Computing</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Han, Boyoung ; Shin, Hojune ; Kim, Yeonghyeon ; Choi, Jina ; Lee, Younho</creator><creatorcontrib>Han, Boyoung ; Shin, Hojune ; Kim, Yeonghyeon ; Choi, Jina ; Lee, Younho</creatorcontrib><description>Although there has been significant progress in homomorphic encryption (HE) technology, a fully homomorphic Naive Bayes (NB) classifier capable of training on HE-encrypted data without decryption has not yet been efficiently developed. This research introduces a new method for approximating homomorphic logarithm calculations with an average relative error under 0.01%. Leveraging the SIMD functionality of the HE framework and a GPU, this technique can compute logarithm values for thousands of encrypted probabilities in about 2.5 seconds. Building upon this, we present a more efficient fully homomorphic NB classifier. Our method can train on a breast cancer dataset in roughly 14.3 seconds and perform query inferences in 0.84 seconds. Compared to the recent privacy-protecting NB classifier from Liu et al. in 2017, which offers a similar security level, our method is estimated to be about 28 times faster.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2024.3438161</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>IEEE</publisher><subject>CKKS ; Data models ; fully homomorphic encryption ; Naive Bayes classifier ; privacy-preserving machine learning ; Protocols ; Public key ; Servers ; Training ; Training data ; Vectors</subject><ispartof>IEEE access, 2024, Vol.12, p.110762-110780</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c261t-6a96ada41e1adb3354206a23fbfb8a65370b34cf7758ad5782a5ddfa679a7dcd3</cites><orcidid>0000-0002-8326-169X ; 0009-0008-8804-963X ; 0000-0003-1767-6165 ; 0009-0004-6190-5791 ; 0009-0004-1851-5712</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10623150$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,860,2096,4010,27610,27900,27901,27902,54908</link.rule.ids></links><search><creatorcontrib>Han, Boyoung</creatorcontrib><creatorcontrib>Shin, Hojune</creatorcontrib><creatorcontrib>Kim, Yeonghyeon</creatorcontrib><creatorcontrib>Choi, Jina</creatorcontrib><creatorcontrib>Lee, Younho</creatorcontrib><title>HEaaN-NB: Non-Interactive Privacy-Preserving Naive Bayes Using CKKS for Secure Outsourced Cloud Computing</title><title>IEEE access</title><addtitle>Access</addtitle><description>Although there has been significant progress in homomorphic encryption (HE) technology, a fully homomorphic Naive Bayes (NB) classifier capable of training on HE-encrypted data without decryption has not yet been efficiently developed. This research introduces a new method for approximating homomorphic logarithm calculations with an average relative error under 0.01%. Leveraging the SIMD functionality of the HE framework and a GPU, this technique can compute logarithm values for thousands of encrypted probabilities in about 2.5 seconds. Building upon this, we present a more efficient fully homomorphic NB classifier. Our method can train on a breast cancer dataset in roughly 14.3 seconds and perform query inferences in 0.84 seconds. Compared to the recent privacy-protecting NB classifier from Liu et al. in 2017, which offers a similar security level, our method is estimated to be about 28 times faster.</description><subject>CKKS</subject><subject>Data models</subject><subject>fully homomorphic encryption</subject><subject>Naive Bayes classifier</subject><subject>privacy-preserving machine learning</subject><subject>Protocols</subject><subject>Public key</subject><subject>Servers</subject><subject>Training</subject><subject>Training data</subject><subject>Vectors</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNkN1Kw0AQhYMoWNQn0Iu8QOr-ZDeJdzVUW5S0EL1eJruzEmm7ZTcp9O1NbBHnYmY4M-e7OFF0T8mUUlI8zspyXtdTRlg65SnPqaQX0YRRWSRccHn5b7-O7kL4JkMNX4XIJlG7mANUSfX8FFdulyx3HXrQXXvAeO3bA-hjsvYY0B_a3VdcwXh4hiOG-DOMSvn2VsfW-bhG3XuMV30XXO81mrjcuH7obrvvu-H1NrqysAl4d5430efL_KNcJO-r12U5e080k7RLJBQSDKQUKZiGc5EyIoFx29gmByl4RhqeaptlIgcjspyBMMaCzArIjDb8JlqeuMbBt9r7dgv-qBy06ldw_kuB71q9QSUHkjBM8MZmqWBFIY0mNJcEU4vW2oHFTyztXQge7R-PEjWGr07hqzF8dQ5_cD2cXC0i_nNIxqkg_Ae7TYDh</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Han, Boyoung</creator><creator>Shin, Hojune</creator><creator>Kim, Yeonghyeon</creator><creator>Choi, Jina</creator><creator>Lee, Younho</creator><general>IEEE</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-8326-169X</orcidid><orcidid>https://orcid.org/0009-0008-8804-963X</orcidid><orcidid>https://orcid.org/0000-0003-1767-6165</orcidid><orcidid>https://orcid.org/0009-0004-6190-5791</orcidid><orcidid>https://orcid.org/0009-0004-1851-5712</orcidid></search><sort><creationdate>2024</creationdate><title>HEaaN-NB: Non-Interactive Privacy-Preserving Naive Bayes Using CKKS for Secure Outsourced Cloud Computing</title><author>Han, Boyoung ; Shin, Hojune ; Kim, Yeonghyeon ; Choi, Jina ; Lee, Younho</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c261t-6a96ada41e1adb3354206a23fbfb8a65370b34cf7758ad5782a5ddfa679a7dcd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CKKS</topic><topic>Data models</topic><topic>fully homomorphic encryption</topic><topic>Naive Bayes classifier</topic><topic>privacy-preserving machine learning</topic><topic>Protocols</topic><topic>Public key</topic><topic>Servers</topic><topic>Training</topic><topic>Training data</topic><topic>Vectors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Han, Boyoung</creatorcontrib><creatorcontrib>Shin, Hojune</creatorcontrib><creatorcontrib>Kim, Yeonghyeon</creatorcontrib><creatorcontrib>Choi, Jina</creatorcontrib><creatorcontrib>Lee, Younho</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Han, Boyoung</au><au>Shin, Hojune</au><au>Kim, Yeonghyeon</au><au>Choi, Jina</au><au>Lee, Younho</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>HEaaN-NB: Non-Interactive Privacy-Preserving Naive Bayes Using CKKS for Secure Outsourced Cloud Computing</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2024</date><risdate>2024</risdate><volume>12</volume><spage>110762</spage><epage>110780</epage><pages>110762-110780</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Although there has been significant progress in homomorphic encryption (HE) technology, a fully homomorphic Naive Bayes (NB) classifier capable of training on HE-encrypted data without decryption has not yet been efficiently developed. This research introduces a new method for approximating homomorphic logarithm calculations with an average relative error under 0.01%. Leveraging the SIMD functionality of the HE framework and a GPU, this technique can compute logarithm values for thousands of encrypted probabilities in about 2.5 seconds. Building upon this, we present a more efficient fully homomorphic NB classifier. Our method can train on a breast cancer dataset in roughly 14.3 seconds and perform query inferences in 0.84 seconds. Compared to the recent privacy-protecting NB classifier from Liu et al. in 2017, which offers a similar security level, our method is estimated to be about 28 times faster.</abstract><pub>IEEE</pub><doi>10.1109/ACCESS.2024.3438161</doi><tpages>19</tpages><orcidid>https://orcid.org/0000-0002-8326-169X</orcidid><orcidid>https://orcid.org/0009-0008-8804-963X</orcidid><orcidid>https://orcid.org/0000-0003-1767-6165</orcidid><orcidid>https://orcid.org/0009-0004-6190-5791</orcidid><orcidid>https://orcid.org/0009-0004-1851-5712</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2169-3536 |
| ispartof | IEEE access, 2024, Vol.12, p.110762-110780 |
| issn | 2169-3536 2169-3536 |
| language | eng |
| recordid | cdi_ieee_primary_10623150 |
| source | IEEE Open Access Journals; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | CKKS Data models fully homomorphic encryption Naive Bayes classifier privacy-preserving machine learning Protocols Public key Servers Training Training data Vectors |
| title | HEaaN-NB: Non-Interactive Privacy-Preserving Naive Bayes Using CKKS for Secure Outsourced Cloud Computing |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T11%3A53%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-doaj_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=HEaaN-NB:%20Non-Interactive%20Privacy-Preserving%20Naive%20Bayes%20Using%20CKKS%20for%20Secure%20Outsourced%20Cloud%20Computing&rft.jtitle=IEEE%20access&rft.au=Han,%20Boyoung&rft.date=2024&rft.volume=12&rft.spage=110762&rft.epage=110780&rft.pages=110762-110780&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2024.3438161&rft_dat=%3Cdoaj_ieee_%3Eoai_doaj_org_article_6b345d253bf7452996dc01860e4fefff%3C/doaj_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10623150&rft_doaj_id=oai_doaj_org_article_6b345d253bf7452996dc01860e4fefff&rfr_iscdi=true |