Show simple item record

dc.contributor.authorZhang, Dalin
dc.contributor.authorYao, Lina
dc.contributor.authorChen, Kaixuan
dc.contributor.authorYang, Zheng
dc.contributor.authorGao, Xin
dc.contributor.authorLiu, Yunhao
dc.date.accessioned2021-05-11T09:50:53Z
dc.date.available2021-05-11T09:50:53Z
dc.date.issued2021
dc.identifier.citationZhang, D., Yao, L., Chen, K., Yang, Z., Gao, X., & Liu, Y. (2021). Preventing Sensitive Information Leakage from Mobile Sensor Signals via IntegrativeTransformation. IEEE Transactions on Mobile Computing, 1–1. doi:10.1109/tmc.2021.3078086
dc.identifier.issn2161-9875
dc.identifier.doi10.1109/TMC.2021.3078086
dc.identifier.urihttp://hdl.handle.net/10754/669165
dc.description.abstractUbiquitous mobile sensors on human activity recognition pose the threat of leaking personal information that is explicitly contained within the time-series sensor signals and can be extracted by attackers. Existing protective methods only support specific sensitive attributes and require massive relevant sensitive ground truth for training, which is unfavourable to users. To fill this gap, we propose a novel data transformation framework for prohibiting the leakage of sensitive information from sensor data. The proposed framework transforms raw sensor data into a new format, where the sensitive information is hidden and the desired information (e.g., human activities) is retained. Training can be conducted without using any personal information as ground truth. Meanwhile, all attributes of sensitive information (e.g., age, gender) can be hidden through a one-time transformation collectively. The experimental results on two multimodal sensor-based human activity datasets manifest the feasibility of the presented framework in hiding users sensitive information (MAE increases 2 times and accuracy degrades 50%) without degrading the usability of the data for activity recognition (2% accuracy degradation).
dc.publisherIEEE
dc.relation.urlhttps://ieeexplore.ieee.org/document/9424974/
dc.relation.urlhttps://ieeexplore.ieee.org/document/9424974/
dc.relation.urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9424974
dc.rights(c) 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
dc.subjectmobile sensors
dc.subjecthuman activity recognition
dc.subjectsensitive information protection
dc.subjectneural network
dc.titlePreventing Sensitive Information Leakage from Mobile Sensor Signals via Integrative Transformation
dc.typeArticle
dc.contributor.departmentComputational Bioscience Research Center (CBRC)
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.contributor.departmentStructural and Functional Bioinformatics Group
dc.identifier.journalIEEE Transactions on Mobile Computing
dc.eprint.versionPost-print
dc.contributor.institutionDepartment of Computer Science, Aalborg University, 1004 Aalborg, Aalborg, Denmark, 9100
dc.contributor.institutionComputer Science and Engineering, University of New South Wales, 7800 Sydney, New South Wales, Australia, 2052
dc.contributor.institutionDepartment of Computer Science, Aalborg University, 1004 Aalborg, Aalborg, Denmark,
dc.contributor.institutionSchool of Software, Tsinghua University, 12442 Beijing, Beijing, China,
dc.identifier.pages1-1
kaust.personGao, Xin
refterms.dateFOA2021-05-11T13:56:17Z


Files in this item

Thumbnail
Name:
2020_TMC.pdf
Size:
3.176Mb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record