Parallelly Running and Privacy-Preserving <i>k</i>-Nearest Neighbor Classification in Outsourced Cloud Computing Environments
Classification is used in various areas where <i>k</i>-nearest neighbor classification is the most popular as it produces efficient results. Cloud computing with powerful resources is one reliable option for handling large-scale data efficiently, but many companies are reluctant to outso...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/24/4132 |
| _version_ | 1797460065903443968 |
|---|---|
| author | Jeongsu Park Dong Hoon Lee |
| author_facet | Jeongsu Park Dong Hoon Lee |
| author_sort | Jeongsu Park |
| collection | DOAJ |
| description | Classification is used in various areas where <i>k</i>-nearest neighbor classification is the most popular as it produces efficient results. Cloud computing with powerful resources is one reliable option for handling large-scale data efficiently, but many companies are reluctant to outsource data due to privacy concerns. This paper aims to implement a privacy-preserving <i>k</i>-nearest neighbor classification (P<i>k</i>NC) in an outsourced environment. Existing work proposed a secure protocol (S<i>k</i>LE/S<i>k</i>SE) to compute <i>k</i> data with the largest/smallest value privately, but this work discloses information. Moreover, S<i>k</i>LE/S<i>k</i>SE requires a secure comparison protocol, and the existing protocols also contain information disclosure problems. In this paper, we propose a new secure comparison and S<i>k</i>LE/S<i>k</i>SE protocols to solve the abovementioned information disclosure problems and implement P<i>k</i>NC with these novel protocols. Our proposed protocols disclose no information and we prove the security formally. Then, through extensive experiments, we demonstrate that the P<i>k</i>NC applying the proposed protocols is also efficient. Especially, the P<i>k</i>NC is suitable for big data analysis to handle large amounts of data, since our S<i>k</i>LE/S<i>k</i>SE is executed for each dataset in parallel. Although the proposed protocols do require efficiency sacrifices to improve security, the running time of our P<i>k</i>NC is still significantly more efficient compared with previously proposed P<i>k</i>NCs. |
| first_indexed | 2024-03-09T17:00:51Z |
| format | Article |
| id | doaj.art-ae58b48c17b040f3a87584bd3efd79a2 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T17:00:51Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-ae58b48c17b040f3a87584bd3efd79a22023-11-24T14:30:51ZengMDPI AGElectronics2079-92922022-12-011124413210.3390/electronics11244132Parallelly Running and Privacy-Preserving <i>k</i>-Nearest Neighbor Classification in Outsourced Cloud Computing EnvironmentsJeongsu Park0Dong Hoon Lee1Graduate School of Information Security, Korea University, Seoul 02841, Republic of KoreaGraduate School of Information Security, Korea University, Seoul 02841, Republic of KoreaClassification is used in various areas where <i>k</i>-nearest neighbor classification is the most popular as it produces efficient results. Cloud computing with powerful resources is one reliable option for handling large-scale data efficiently, but many companies are reluctant to outsource data due to privacy concerns. This paper aims to implement a privacy-preserving <i>k</i>-nearest neighbor classification (P<i>k</i>NC) in an outsourced environment. Existing work proposed a secure protocol (S<i>k</i>LE/S<i>k</i>SE) to compute <i>k</i> data with the largest/smallest value privately, but this work discloses information. Moreover, S<i>k</i>LE/S<i>k</i>SE requires a secure comparison protocol, and the existing protocols also contain information disclosure problems. In this paper, we propose a new secure comparison and S<i>k</i>LE/S<i>k</i>SE protocols to solve the abovementioned information disclosure problems and implement P<i>k</i>NC with these novel protocols. Our proposed protocols disclose no information and we prove the security formally. Then, through extensive experiments, we demonstrate that the P<i>k</i>NC applying the proposed protocols is also efficient. Especially, the P<i>k</i>NC is suitable for big data analysis to handle large amounts of data, since our S<i>k</i>LE/S<i>k</i>SE is executed for each dataset in parallel. Although the proposed protocols do require efficiency sacrifices to improve security, the running time of our P<i>k</i>NC is still significantly more efficient compared with previously proposed P<i>k</i>NCs.https://www.mdpi.com/2079-9292/11/24/4132cloud computingbig data analysisk-nearest neighbor classificationprivacy-preserving computation |
| spellingShingle | Jeongsu Park Dong Hoon Lee Parallelly Running and Privacy-Preserving <i>k</i>-Nearest Neighbor Classification in Outsourced Cloud Computing Environments Electronics cloud computing big data analysis k-nearest neighbor classification privacy-preserving computation |
| title | Parallelly Running and Privacy-Preserving <i>k</i>-Nearest Neighbor Classification in Outsourced Cloud Computing Environments |
| title_full | Parallelly Running and Privacy-Preserving <i>k</i>-Nearest Neighbor Classification in Outsourced Cloud Computing Environments |
| title_fullStr | Parallelly Running and Privacy-Preserving <i>k</i>-Nearest Neighbor Classification in Outsourced Cloud Computing Environments |
| title_full_unstemmed | Parallelly Running and Privacy-Preserving <i>k</i>-Nearest Neighbor Classification in Outsourced Cloud Computing Environments |
| title_short | Parallelly Running and Privacy-Preserving <i>k</i>-Nearest Neighbor Classification in Outsourced Cloud Computing Environments |
| title_sort | parallelly running and privacy preserving i k i nearest neighbor classification in outsourced cloud computing environments |
| topic | cloud computing big data analysis k-nearest neighbor classification privacy-preserving computation |
| url | https://www.mdpi.com/2079-9292/11/24/4132 |
| work_keys_str_mv | AT jeongsupark parallellyrunningandprivacypreservingikinearestneighborclassificationinoutsourcedcloudcomputingenvironments AT donghoonlee parallellyrunningandprivacypreservingikinearestneighborclassificationinoutsourcedcloudcomputingenvironments |