TY - GEN
T1 - Multi-Kernel, Deep Neural Network and Hybrid Models for Privacy Preserving Machine Learning
AU - Al, Mert
AU - Chanyaswad, Thee
AU - Kung, Sun Yuan
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/10
Y1 - 2018/9/10
N2 - The rapid rise of IoT and Big Data can facilitate the use of data to enhance our quality of life. However, the omnipresent and sensitive nature of data can simultaneously generate privacy concerns. Hence, there is a strong need to develop techniques that ensure the data serve the intended purposes, but not for prying into one's sensitive information. We address this challenge via utility maximizing lossy compression of data. Our techniques combine the mathematical rigor of Kernel Learning models with the structural richness of Deep Neural Networks, and lead to the novel Multi-Kernel Learning and Hybrid Learning models. We systematically construct the proposed models in progressive stages, as motivated by the cumulative improvement in the experimental results from the two previously non-intersecting regimes, namely, Kernel Learning and Deep Neural Networks. The final experimental results of the three proposed models on three mobile sensing datasets show that, not only are our methods able to improve the utility prediction accuracies, but they can also cause sensitive predictions to perform nearly as bad as random guessing, resulting in a win-win situation in terms of utility and privacy.
AB - The rapid rise of IoT and Big Data can facilitate the use of data to enhance our quality of life. However, the omnipresent and sensitive nature of data can simultaneously generate privacy concerns. Hence, there is a strong need to develop techniques that ensure the data serve the intended purposes, but not for prying into one's sensitive information. We address this challenge via utility maximizing lossy compression of data. Our techniques combine the mathematical rigor of Kernel Learning models with the structural richness of Deep Neural Networks, and lead to the novel Multi-Kernel Learning and Hybrid Learning models. We systematically construct the proposed models in progressive stages, as motivated by the cumulative improvement in the experimental results from the two previously non-intersecting regimes, namely, Kernel Learning and Deep Neural Networks. The final experimental results of the three proposed models on three mobile sensing datasets show that, not only are our methods able to improve the utility prediction accuracies, but they can also cause sensitive predictions to perform nearly as bad as random guessing, resulting in a win-win situation in terms of utility and privacy.
KW - Big data
KW - Classification
KW - Discriminant information
KW - Kernel methods
KW - Privacy preserving machine learning
UR - http://www.scopus.com/inward/record.url?scp=85054238831&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85054238831&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2018.8462336
DO - 10.1109/ICASSP.2018.8462336
M3 - Conference contribution
AN - SCOPUS:85054238831
SN - 9781538646588
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 2891
EP - 2895
BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
Y2 - 15 April 2018 through 20 April 2018
ER -