Differentially private tensor deep computation for cyber-physical-social systems

Simple item page
dc.creatorGati, Nicholaus J.
dc.creatorYang, Laurence T.
dc.creatorFeng, Jun
dc.creatorZhang, Shunli
dc.creatorRen, Zhian
dc.date2021-05-06T08:48:46Z
dc.date2021-05-06T08:48:46Z
dc.date2020
dc.date.accessioned2022-10-20T13:47:43Z
dc.date.available2022-10-20T13:47:43Z
dc.descriptionAbstract. Full-text article available at: https://doi.org/10.1016/j.ins.2019.07.036
dc.descriptionIn the recent past, deep learning has received remarkable acceptance in real-world applications. Social computing expands the existing notion of cyber space and physical space to a more advance cyber–physical–social system (CPSS). Therefore, deep learning provides a propitious technique for accurate mining of information from CPSS, thus facilitates CPSS to offer services of exceptional quality efficiently. However, most of the current deep learning methods are struggling to keep up with the ever-increasing heterogeneous and highly nonlinear dissemination of data. Furthermore, the advancement of deep learning presents privacy concerns. This article proposes a deep private tensor autoencoder (dPTAE), where tensors are used for data representation, and differential privacy guarantees strong privacy. The core idea of our work is to enforce differential privacy through noise injection into the objective functions instead of the results they produce. In addition, the proposed method preserves the privacy of information shared amongst CPSS in smart environments. We applied dPTAE on three representative data sets. Rigorous experimental evaluations and theoretical analysis demonstrate that dPTAE is significantly effective and efficient.
dc.identifierGati, N. J., Yang, L. T., Feng, J., Zhang, S., & Ren, Z. (2020). Differentially private tensor deep computation for cyber-physical-social systems. IEEE Transactions on Computational Social Systems, 8(1), 236 - 245,
dc.identifierDOI: https://doi.org/10.1016/j.ins.2019.07.036
dc.identifierURL: https://ieeexplore.ieee.org/abstract/document/9134400
dc.identifierhttp://hdl.handle.net/20.500.12661/2964
dc.identifier.urihttp://hdl.handle.net/20.500.12661/2964
dc.languageen
dc.publisherIEEE
dc.subjectSocial computing
dc.subjectCyber space
dc.subjectPhysical space
dc.subjectCyber–Physical–Social System
dc.subjectCPSS
dc.subjectMining
dc.subjectNoise injection
dc.subjectBig data analytics
dc.titleDifferentially private tensor deep computation for cyber-physical-social systems
dc.typeArticle

Files

Collections

Research Articles