Utility-Preserving Face Anonymization via Differentially Private Feature Operations

• Main Authors: Li, Chengqi, Simionescu, Sarah, He, Wenbo, Qiao, Sanzheng, Kara, Nadjia, Talhi, Chamseddine
• Format: Conference Proceeding
• Language: English
• Subjects: Benchmark testing; Classification algorithms; Differential privacy; Face anonymization; Inference algorithms; Information filtering; Numerical models; Perturbation methods; Privacy; Utility and privacy tradeoff
• ISSN: 2641-9874
• DOI: 10.1109/INFOCOM52122.2024.10621407

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.