Target-based privacy preserving association rule mining

Ahluwalia, Madhu V.; Gangopadhyay, Aryya; Chen, Zhiyuan; Yesha, Yelena

doi:10.1145/1982185.1982395

Cited by 1 publication

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a different work [4], the TBDS algorithm is applied in conjunction with the DWT algorithm to prove that discrete wavelet transformation over changed data is viable because it generates highly accurate association rules and maintains data privacy when few changes occur between the source and the target. The approach used is called Wavelet Coefficient Maintenance (WCM).…”

Section:  Nmentioning

confidence: 99%

“…Let the partition size be four rows per partition. The target database then stores on its space, tables of partition definition (Partition Information of S) 4 , and transformation (Transformed Dataset T) of the initial synchronization (Source Dataset S). A copy of the transformation with rows IDs pruned off (Miner's Transformed Dataset T) is exchanged with the miner.…”

Section: Target-based Privatized Incremental Rule Update Algorithmmentioning

confidence: 99%

“…In the first case, we must ensure that the transformed delta does not reveal any element of the raw delta on which it is based. We refer to the high level of privacy obtained in such case by authors of [4]. The authors use information theory approach to prove that wavelet transforms do indeed provide higher levels of conditional privacy than random projection and kd-tree.…”

Section: Preserving Privacymentioning

confidence: 99%

See 2 more Smart Citations

Target-Based, Privacy Preserving, and Incremental Association Rule Mining

Ahluwalia¹,

Gangopadhyay²,

Chen³

et al. 2017

IEEE Trans. Serv. Comput.

Self Cite

View full text Add to dashboard Cite

We consider a special case in association rule mining where mining is conducted by a third party over data located at a central location that is updated from several source locations. The data at the central location is at rest while that flowing in through source locations is in motion. We impose some limitations on the source locations, so that the central target location tracks and privatizes changes and a third party mines the data incrementally. Our results show high efficiency, privacy and accuracy of rules for small to moderate updates in large volumes of data. We believe that the framework we develop is therefore applicable and valuable for mining big data.

show abstract

Section:  Nmentioning

confidence: 99%

Section: Target-based Privatized Incremental Rule Update Algorithmmentioning

confidence: 99%

Section: Preserving Privacymentioning

confidence: 99%

See 1 more Smart Citation