Show simple item record

dc.contributor.authorZhang, D
dc.contributor.authorYao, L
dc.contributor.authorChen, K
dc.contributor.authorLong, G
dc.contributor.authorWang, S
dc.date.accessioned2020-03-23T03:13:13Z
dc.date.available2020-03-23T03:13:13Z
dc.date.issued2019
dc.identifier.isbn9781728146034
dc.identifier.issn1550-4786
dc.identifier.doi10.1109/ICDM.2019.00197
dc.identifier.urihttp://hdl.handle.net/10072/392542
dc.description.abstractSharing ubiquitous mobile sensor data, especially physiological data, raises potential risks of leaking physical and demographic information that can be inferred from the time series sensor data. Existing sensitive information protection mechanisms that depend on data transformation are effective only on a particular sensitive attribute, together with usually requiring the labels of sensitive information for training. Considering this gap, we propose a novel user sensitive information protection framework without using a sensitive training dataset or being validated on protecting only one specific sensitive information. The presented approach transforms raw sensor data into a new format that has a 'style' (sensitive information) of random noise and a 'content' (desired information) of the raw sensor data, thus is free of user sensitive information for training and able to collectively protect all sensitive information at once. Our implementation and experiments on two real-world multisensor human activity datasets demonstrate that the proposed data transformation technique can achieve the protection for all sensitive information at once without requiring the knowledge of users' personal attributes for training, and simultaneously preserve the usability of the new transformed data with regard to inferring human activities with insignificant performance loss.
dc.description.peerreviewedYes
dc.publisherIEEE
dc.relation.ispartofconferencename2019 IEEE International Conference on Data Mining (ICDM 2019)
dc.relation.ispartofconferencetitleProceedings - IEEE International Conference on Data Mining, ICDM
dc.relation.ispartofdatefrom2019-11-08
dc.relation.ispartofdateto2019-11-11
dc.relation.ispartoflocationBeijing, China
dc.relation.ispartofpagefrom1498
dc.relation.ispartofpageto1503
dc.relation.ispartofvolume2019-November
dc.subject.fieldofresearchData Format
dc.subject.fieldofresearchInformation Systems
dc.subject.fieldofresearchcode0804
dc.subject.fieldofresearchcode0806
dc.titleCollective protection: Preventing sensitive inferences via integrative transformation
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationZhang, D; Yao, L; Chen, K; Long, G; Wang, S, Collective protection: Preventing sensitive inferences via integrative transformation, Proceedings - IEEE International Conference on Data Mining, ICDM, 2019, 2019-November, pp. 1498-1503
dc.date.updated2020-03-23T03:11:20Z
gro.hasfulltextNo Full Text
gro.griffith.authorWang, Sen


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record