Home
Scholarly Works
Utility-Preserving Face Anonymization via...
Conference

Utility-Preserving Face Anonymization via Differentially Private Feature Operations

Abstract

Facial images play a crucial role in many web and security applications, but their uses come with notable privacy risks. Despite the availability of various face anonymization algorithms, they often fail to withstand advanced attacks while struggling to maintain utility for subsequent applications. We present two novel face anonymization algorithms that utilize feature operations to overcome these limitations. The first algorithm utilizes perturbation and matching of high-level features, whereas the second algorithm enhances this approach by also incorporating perturbation of low-level features along with regularization. These algorithms significantly enhance the utility of anonymized images while ensuring differential privacy. Additionally, we introduce a task-based benchmark to enable fair and comprehensive evaluations of privacy and utility across different algorithms. Through experiments, we demonstrate that our algorithms outperform others in preserving the utility of anonymized facial images in classification tasks while effectively protecting against a wide range of attacks.

Authors

Li C; Simionescu S; He W; Qiao S; Kara N; Talhi C

Volume

00

Pagination

pp. 2279-2288

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Publication Date

May 23, 2024

DOI

10.1109/infocom52122.2024.10621407

Name of conference

IEEE INFOCOM 2024 - IEEE Conference on Computer Communications
View published work (Non-McMaster Users)

Contact the Experts team