DML
DML Sharif University of Technology
Deep Private-Feature Extraction
  Jan   2020      
S.A. Osia , A. Taheri , A.S. Shamsabadi , K. Katevas , H. Haddadi and H.R. Rabiee
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
Type
Journal
Publisher
IEEE
Volume
32
Issue
1
Pages
54-66