Search Results for author:
Found 3 papers, 0 papers with code
Divide and Conquer: a Two-Step Method for High Quality Face De-identification with Model Explainability
To address these issues, we propose IDeudemon, which employs a "divide and conquer" strategy to protect identity and preserve utility step by step while maintaining good explainability.
IdentityDP: Differential Private Identification Protection for Face Images
We propose IdentityDP, a face anonymization framework that combines a data-driven deep neural network with a differential privacy (DP) mechanism.
Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation
The popularization of intelligent devices including smartphones and surveillance cameras results in more serious privacy issues.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
