Deep Private-Feature Extraction
This addresses privacy concerns for users sharing data with service providers, but it appears incremental as it builds on existing privacy-preserving techniques with a novel measure.
The paper tackles the problem of protecting sensitive information when sharing data with service providers by introducing Deep Private-Feature Extractor (DPFE), a deep model that uses information-theoretic constraints and log-rank privacy to achieve high accuracy for primary tasks while preserving privacy on benchmark image datasets.
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 tradeoff. We then implement and evaluate the performance of DPFE on smartphones to understand its complexity, resource demands, and efficiency tradeoffs. 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 features.