Achieving correlated differential privacy of big data publication. Issue 82 (May 2019)

• Record Type: Journal Article
• Authors: Lv, Denglong; Zhu, Shibing
• Is Part Of: Computers & security. Issue 82(2019)
• Page Start: 184
• Page End: 195
• Publication Date: 2019-05
• Subjects: Big data -- Correlated datasets -- Differential privacy -- Maximum information coefficient -- Machine learning; Computer security -- Periodicals; Electronic data processing departments -- Security measures -- Periodicals; 005.805
• DOI: 10.1016/j.cose.2018.12.017
• Languages: English
• ISSNs: 0167-4048

Abstract

Abstract: For protecting privacy of correlated data in big data, k-CRDP and r-CBDP models are proposed. Firstly r-CBDP uses MIC and machine learning to determine dependencies between data, accurately calculates correlated sensitivity, then divides big data into independent blocks, and implements k-CRDP for blocks to achieve big data correlated differential privacy.