Deep Private-Feature Extraction

Seyed Ali Osia, Ali Taheri, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Hamid R. RabieeIEEE TKDE 2020 · OpenReview

Abstract

We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service provider, DPFE enables the user to prevent certain sensitive information from being shared with a service provider, while allowing them to extract approved information using their model. We introduce and utilize the log-rank privacy, a novel measure to assess the effectiveness of DPFE in removing sensitive information and compare different models based on their accuracy-privacy trade-off. We then implement and evaluate the performance of DPFEon smartphones to understand its complexity, resource demands, and efficiency trade-offs. Our results on benchmark image datasets demonstrate that under moderate resource utilization, DPFE can achieve high accuracy for primary tasks while preserving the privacy of sensitive information.
BibTeX
@article{osia2020deep,
  author = {Seyed Ali Osia and Ali Taheri and Ali Shahin Shamsabadi and Kleomenis Katevas and Hamed Haddadi and Hamid R. Rabiee},
  title = {{Deep Private-Feature Extraction}},
  journal = {IEEE Trans. Knowl. Data Eng.},
  year = {2020},
  url = {https://openreview.net/forum?id=ZpK_z-YoDiO},
}

Loading related content...

Figure