Corpus ID: 220920084

Privacy Enhancing Machine Learning via Removal of Unwanted Dependencies

@article{Al2020PrivacyEM,
  title={Privacy Enhancing Machine Learning via Removal of Unwanted Dependencies},
  author={Mert Al and S. Yagli and S. Kung},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.15710}
}
The rapid rise of IoT and Big Data has facilitated copious data driven applications to enhance our quality of life. However, the omnipresent and all-encompassing nature of the data collection can generate privacy concerns. Hence, there is a strong need to develop techniques that ensure the data serve only the intended purposes, giving users control over the information they share. To this end, this paper studies new variants of supervised and adversarial learning methods, which remove the… Expand

References

SHOWING 1-10 OF 46 REFERENCES
Face Synthesis for Eyeglass-Robust Face Recognition
  • 18
  • Highly Influential
  • PDF
Compressive Privacy: From Information\/Estimation Theory to Machine Learning [Lecture Notes]
  • S. Kung
  • Computer Science
  • IEEE Signal Processing Magazine
  • 2017
  • 24
  • Highly Influential
mHealthDroid: A Novel Framework for Agile Development of Mobile Health Applications
  • 185
  • Highly Influential
  • PDF
A Public Domain Dataset for Human Activity Recognition using Smartphones
  • 865
  • Highly Influential
  • PDF
On the empirical estimation of integral probability metrics
  • 144
  • Highly Influential
  • PDF
Theory of Reproducing Kernels.
  • 4,731
  • Highly Influential
  • PDF
Wasserstein Distance Guided Representation Learning for Domain Adaptation
  • 231
  • Highly Influential
Least Squares Generative Adversarial Networks
  • 1,940
  • Highly Influential
  • PDF
Wasserstein GAN
  • 2,216
  • Highly Influential
  • PDF
A Kernel Two-Sample Test
  • 1,934
  • Highly Influential
  • PDF
...
1
2
3
4
5
...